# Observing and Controlling Features in Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2603.05487 · HTML: https://mlsanity.com/paper/2603.05487/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in VLA architectures and generalization, one of 13 directions in Vision-language-action models.
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Placed in

- Vision-language-action models / [VLA architectures and generalization](https://mlsanity.com/vla/vla-architectures-and-generalization/)

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [The Geometry of Categorical and Hierarchical Concepts in Large Language Models](https://mlsanity.com/paper/2406.01506/) (2024)
- [Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications](https://mlsanity.com/paper/2510.07077/) (2025)
- [Controlling Language and Diffusion Models by Transporting Activations](https://mlsanity.com/paper/2410.23054/) (2024)
- [Mechanistic interpretability for steering vision-language-action models](https://mlsanity.com/paper/2509.00328/) (2025)
- [HyperSteer: Activation Steering at Scale with Hypernetworks](https://mlsanity.com/paper/2506.03292/) (2025)
- [LiSeCo: Linear Semantic Control for Language Generation](https://mlsanity.com/paper/2405.15454/) (2024)
- [Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture](https://mlsanity.com/paper/2502.04558/) (2025)
- [Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations](https://mlsanity.com/paper/2511.22697/) (2025)
- [Emergent World Representations in OpenVLA](https://mlsanity.com/paper/2509.24559/) (2025)

## Built on by (most cited first, 16 of 16)

- [Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models](https://mlsanity.com/paper/2603.19183/) (2026)
- [Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering](https://mlsanity.com/paper/2606.12299/) (2026)
- [Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control](https://mlsanity.com/paper/2607.14943/) (2026)
- [Decoding Task Progress from VLA Representations](https://mlsanity.com/paper/2608.13474/) (2026)
- [Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies](https://mlsanity.com/paper/2605.17204/) (2026)
- [Present but Not Remembered: Auditing How Frozen VLAs Encode, Deploy, and Steer Visual History](https://mlsanity.com/paper/2607.03372/) (2026)
- [DiMaS: Distribution Matching for Steering Vision-Language-Action Models](https://mlsanity.com/paper/2607.14280/) (2026)
- [Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models](https://mlsanity.com/paper/2606.10495/) (2026)
- [Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models](https://mlsanity.com/paper/2608.02497/) (2026)
- [Multimodal Model Diffing for Feature Discovery and Control](https://mlsanity.com/paper/2608.09928/) (2026)
- [FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy](https://mlsanity.com/paper/2608.16697/) (2026)
- [What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior](https://mlsanity.com/paper/2609.24576/) (2026)
- [The Linear Representation Hypothesis for Vision-Language-Action Models](https://mlsanity.com/paper/2609.30996/) (2026)
- [The Low-Rank Structure of VLA Reinforcement Learning](https://mlsanity.com/paper/2609.34599/) (2026)
- [Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models](https://mlsanity.com/paper/2610.03498/) (2026)
- [Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors?](https://mlsanity.com/paper/2610.06078/) (2026)

## Abstract (arXiv)

Vision-Language-Action models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal inputs/outputs and often hybrid nature of transformer and diffusion heads. This is part of the reason why insights from mechanistic interpretability in LLMs, which explain how the internal model representations relate to their output behavior, do not trivially transfer to VLA counterparts. In this work, we investigate whether VLA internal representations support lightweight behavioral steering without retraining. Across four frontier VLA models, linear observers recover state- and action-relevant information in both autoregressive and transformer--flow-matching architectures, and provide robust directions to causally alter VLA outputs. Building on this, we introduce a controller that minimally modifies representations to place observer predictions within prescribed target intervals. Closed-loop experiments with π0.5 in the LIBERO simulator and on DROID hardware demonstrate improved constraint satisfaction while retaining task performance, with only approximately 1% inference overhead. Together, these experiments show that lightweight linear interventions can reliably steer VLA behavior while preserving closed-loop capabilities, enabling alignment with user preferences and task requirements without fine-tuning.