# SAEs Are Good for Steering -- If You Select the Right Features

arXiv: https://arxiv.org/abs/2505.20063 · HTML: https://mlsanity.com/paper/2505.20063/

## Key facts

- Cited by 78 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 36 of its 66 references that are in the map.
- First posted on arXiv 26 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 36)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [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)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [Linguistic Knowledge and Transferability of Contextual Representations](https://mlsanity.com/paper/1903.08855/) (2019)
- [Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders](https://mlsanity.com/paper/2407.14435/) (2024)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [What do Neural Machine Translation Models Learn about Morphology?](https://mlsanity.com/paper/1704.03471/) (2017)
- [The Remarkable Robustness of LLMs: Stages of Inference?](https://mlsanity.com/paper/2406.19384/) (2024)
- [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](https://mlsanity.com/paper/2410.20526/) (2024)
- [On Identifiability in Transformers](https://mlsanity.com/paper/1908.04211/) (2019)
- [Identifying and Controlling Important Neurons in Neural Machine Translation](https://mlsanity.com/paper/1811.01157/) (2018)
- [Universal Neurons in GPT2 Language Models](https://mlsanity.com/paper/2401.12181/) (2024)
- [Enhancing Automated Interpretability with Output-Centric Feature Descriptions](https://mlsanity.com/paper/2501.08319/) (2025)
- [Extending Activation Steering to Broad Skills and Multiple Behaviours](https://mlsanity.com/paper/2403.05767/) (2024)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)

## Built on by (most cited first, 30 of 78)

- [Persona Features Control Emergent Misalignment](https://mlsanity.com/paper/2506.19823/) (2025)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [The Rogue Scalpel: Activation Steering Compromises LLM Safety](https://mlsanity.com/paper/2509.22067/) (2025)
- [Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models](https://mlsanity.com/paper/2605.11887/) (2026)
- [Position: Use Sparse Autoencoders to Discover Unknowns](https://mlsanity.com/paper/2506.23845/) (2025)
- [Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability](https://mlsanity.com/paper/2511.05541/) (2025)
- [CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features](https://mlsanity.com/paper/2508.12535/) (2025)
- [CRISP: Persistent Concept Unlearning via Sparse Autoencoders](https://mlsanity.com/paper/2508.13650/) (2025)
- [The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching](https://mlsanity.com/paper/2606.27510/) (2026)
- [Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement](https://mlsanity.com/paper/2509.23799/) (2025)
- [Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders](https://mlsanity.com/paper/2510.03659/) (2025)
- [SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder](https://mlsanity.com/paper/2510.05081/) (2025)
- [From Weights to Activations: Is Steering the Next Frontier of Adaptation?](https://mlsanity.com/paper/2604.14090/) (2026)
- [From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?](https://mlsanity.com/paper/2512.15134/) (2025)
- [DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2602.05859/) (2026)
- [Interpretable and Steerable Concept Bottleneck Sparse Autoencoders](https://mlsanity.com/paper/2512.10805/) (2025)
- [Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers](https://mlsanity.com/paper/2603.01437/) (2026)
- [Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens](https://mlsanity.com/paper/2604.02608/) (2026)
- [Steering at the Source: Style Modulation Heads for Robust Persona Control](https://mlsanity.com/paper/2603.13249/) (2026)
- [Evaluating Sparse Autoencoders for Monosemantic Representation](https://mlsanity.com/paper/2508.15094/) (2025)
- [AlignSAE: Concept-Aligned Sparse Autoencoders](https://mlsanity.com/paper/2512.02004/) (2025)
- [The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models](https://mlsanity.com/paper/2602.08159/) (2026)
- [Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks](https://mlsanity.com/paper/2602.22719/) (2026)
- [Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models](https://mlsanity.com/paper/2605.10971/) (2026)
- [Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines](https://mlsanity.com/paper/2605.31183/) (2026)
- [CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders](https://mlsanity.com/paper/2509.00691/) (2025)
- [Can SAEs reveal and mitigate racial biases of LLMs in healthcare?](https://mlsanity.com/paper/2511.00177/) (2025)
- [Geometric Routing Enables Causal Expert Control in Mixture of Experts](https://mlsanity.com/paper/2604.14434/) (2026)
- [Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence](https://mlsanity.com/paper/2608.12036/) (2026)
- [Calibrating Lightweight Sparse Autoencoder Feature Steering](https://mlsanity.com/paper/2506.12576/) (2025)

## Abstract (arXiv)

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept - without requiring labeled data. Current methods identify SAE features to steer by analyzing the input tokens that activate them. However, recent work has highlighted that activations alone do not fully describe the effect of a feature on the model's output. In this work, we draw a distinction between two types of features: input features, which mainly capture patterns in the model's input, and output features, which have a human-understandable effect on the model's output. We propose input and output scores to characterize and locate these types of features, and show that high values for both scores rarely co-occur in the same features. These findings have practical implications: after filtering out features with low output scores, we obtain 2-3x improvements when steering with SAEs, making them competitive with supervised methods.