# Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis

arXiv: https://arxiv.org/abs/2605.03160 · HTML: https://mlsanity.com/paper/2605.03160/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in SAE features and their applications, one of 13 directions in Mechanistic interpretability.
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 4 May 2026.

## 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 30)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (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)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Not All Language Model Features Are One-Dimensionally Linear](https://mlsanity.com/paper/2405.14860/) (2024)
- [A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders](https://mlsanity.com/paper/2409.14507/) (2024)
- [The Geometry of Categorical and Hierarchical Concepts in Large Language Models](https://mlsanity.com/paper/2406.01506/) (2024)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](https://mlsanity.com/paper/2410.20526/) (2024)
- [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022)
- [SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability](https://mlsanity.com/paper/2503.09532/) (2025)
- [Are Sparse Autoencoders Useful? A Case Study in Sparse Probing](https://mlsanity.com/paper/2502.16681/) (2025)
- [Automatically Interpreting Millions of Features in Large Language Models](https://mlsanity.com/paper/2410.13928/) (2024)
- [Sparse Autoencoders Do Not Find Canonical Units of Analysis](https://mlsanity.com/paper/2502.04878/) (2025)
- [SAEs Are Good for Steering -- If You Select the Right Features](https://mlsanity.com/paper/2505.20063/) (2025)
- [Rigorously Assessing Natural Language Explanations of Neurons](https://mlsanity.com/paper/2309.10312/) (2023)
- [Enhancing Automated Interpretability with Output-Centric Feature Descriptions](https://mlsanity.com/paper/2501.08319/) (2025)
- [Towards Reliable Evaluation of Behavior Steering Interventions in LLMs](https://mlsanity.com/paper/2410.17245/) (2024)
- [The Rogue Scalpel: Activation Steering Compromises LLM Safety](https://mlsanity.com/paper/2509.22067/) (2025)
- [FADE: Why Bad Descriptions Happen to Good Features](https://mlsanity.com/paper/2502.16994/) (2025)

## Abstract (arXiv)

The standard protocol for interpreting sparse-autoencoder (SAE) features labels each feature from its top-activating contexts and validates the label by steering that single feature at a typical magnitude. We argue that this inspects one cell of a larger steering grid, steering condition (single feature, joint feature set, matched random direction) crossed with steering coefficient, and show that other cells carry information that changes the label. On Qwen3-1.7B-Instruct and Gemma-2-2B-it, with the matched-geometry control extended to Llama-3.1-8B-Instruct: (1) features labelled AI self-disclaimer from their top contexts switch to a second surface form under steering, a contemplative voice on Qwen, a collective we-voice on Gemma, so the label names an activation regime, not the causal axis; two anchor features separate genuine mode switches from monotonic response and from breakdown. (2) Three near-orthogonal features that are individually substitutable are jointly necessary for grounded composition: joint suppression collapses unrelated control tasks into placeholder text that single-feature suppression at the same coefficient leaves intact. (3) A matched-geometry random-direction control shows the collapse is direction-pattern-dependent, not magnitude-dependent: at the same residual-stream distortion, feature directions damage unrelated tasks where magnitude-matched random directions do not, with non-overlapping 95% confidence intervals on all three models, including the one SAE trained on the model it is applied to.