# SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models

arXiv: https://arxiv.org/abs/2505.16188 · HTML: https://mlsanity.com/paper/2505.16188/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in SAE features and their applications, one of 13 directions in Mechanistic interpretability.
- Builds on 33 of its 41 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- Mechanistic interpretability / [SAE features and their applications](https://mlsanity.com/mechinterp/sae-features-and-their-applications/)

## Builds on (most cited first, 30 of 33)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [Are Sparse Autoencoders Useful? A Case Study in Sparse Probing](https://mlsanity.com/paper/2502.16681/) (2025)
- [Improving Steering Vectors by Targeting Sparse Autoencoder Features](https://mlsanity.com/paper/2411.02193/) (2024)
- [Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories](https://mlsanity.com/paper/2406.00034/) (2024)
- [Word Embeddings Are Steers for Language Models](https://mlsanity.com/paper/2305.12798/) (2023)
- [Improving Activation Steering in Language Models with Mean-Centring](https://mlsanity.com/paper/2312.03813/) (2023)
- [Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks](https://mlsanity.com/paper/2411.16721/) (2024)
- [Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding](https://mlsanity.com/paper/2502.01563/) (2025)
- [A Unified Understanding and Evaluation of Steering Methods](https://mlsanity.com/paper/2502.02716/) (2025)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models](https://mlsanity.com/paper/2502.11356/) (2025)
- [On the Relationship between Truth and Political Bias in Language Models](https://mlsanity.com/paper/2409.05283/) (2024)
- [Controlling Large Language Model Agents with Entropic Activation Steering](https://mlsanity.com/paper/2406.00244/) (2024)
- [Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution](https://mlsanity.com/paper/2410.00153/) (2024)
- [Efficient fair PCA for fair representation learning](https://mlsanity.com/paper/2302.13319/) (2023)
- [Sparse Autoencoder Features for Classifications and Transferability](https://mlsanity.com/paper/2502.11367/) (2025)

## Built on by (most cited first, 29 of 29)

- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement](https://mlsanity.com/paper/2509.23799/) (2025)
- [SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models](https://mlsanity.com/paper/2511.20820/) (2025)
- [All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs](https://mlsanity.com/paper/2605.12671/) (2026)
- [Evaluating Sparse Autoencoders for Monosemantic Representation](https://mlsanity.com/paper/2508.15094/) (2025)
- [Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs](https://mlsanity.com/paper/2603.03415/) (2026)
- [Quantifying Conversation Drift in MCP via Latent Polytope](https://mlsanity.com/paper/2508.06418/) (2025)
- [SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning](https://mlsanity.com/paper/2511.16324/) (2025)
- [YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation](https://mlsanity.com/paper/2601.08441/) (2026)
- [Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering](https://mlsanity.com/paper/2601.22010/) (2026)
- [Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders](https://mlsanity.com/paper/2604.25866/) (2026)
- [Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models](https://mlsanity.com/paper/2605.25941/) (2026)
- [Position: AI Safety Requires Effective Controllability](https://mlsanity.com/paper/2605.27117/) (2026)
- [SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization](https://mlsanity.com/paper/2606.08496/) (2026)
- [CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits](https://mlsanity.com/paper/2608.05732/) (2026)
- [REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features](https://mlsanity.com/paper/2608.28233/) (2026)
- [Enhancing SAE-based Steering via Neighbor Integrated Feature Selection](https://mlsanity.com/paper/2608.28806/) (2026)
- [Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder](https://mlsanity.com/paper/2506.20083/) (2025)
- [Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs](https://mlsanity.com/paper/2602.19157/) (2026)
- [Steered Generation via Gradient-Based Optimization on Sparse Query Features](https://mlsanity.com/paper/2605.23040/) (2026)
- [Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations](https://mlsanity.com/paper/2607.17117/) (2026)
- [SAE-StatSteer: Statistical Consensus Feature Selection for Optimization-Free Activation Steering of Large Language Models](https://mlsanity.com/paper/2607.19364/) (2026)
- [Measuring Semantic Abstractness of SAE Features via Nonlocality](https://mlsanity.com/paper/2608.10537/) (2026)
- [EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders](https://mlsanity.com/paper/2608.28191/) (2026)
- [IDEEA: training-free Input-Dependent stEEring via Activation cluster matching](https://mlsanity.com/paper/2609.02089/) (2026)
- [When Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap](https://mlsanity.com/paper/2609.21662/) (2026)
- [STR: Supervised Transcoder Replacement for Reducing Steering Side Effects](https://mlsanity.com/paper/2609.32519/) (2026)
- [MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation](https://mlsanity.com/paper/2609.38718/) (2026)
- [SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement Learning](https://mlsanity.com/paper/2610.16104/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper introduces a novel supervised steering approach that operates in sparse, interpretable representation spaces. We employ sparse autoencoders (SAEs) to obtain sparse latent representations that aim to disentangle semantic attributes from model activations. Then we train linear classifiers to identify a small subspace of task-relevant dimensions in latent representations. Finally, we learn supervised steering vectors constrained to this subspace, optimized to align with target behaviors. Experiments across sentiment, truthfulness, and political polarity steering tasks with multiple LLMs demonstrate that our supervised steering vectors achieve higher success rates with minimal degradation in generation quality compared to existing methods. Further analysis reveals that a notably small subspace is sufficient for effective steering, enabling more targeted and interpretable interventions. Our implementation is publicly available at https://github.com/Ineedanamehere/SAE-SSV.