# Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies

arXiv: https://arxiv.org/abs/2605.17204 · HTML: https://mlsanity.com/paper/2605.17204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 17 May 2026.

## Placed in

- Vision-language-action models / [Generalist VLA models and benchmarks](https://mlsanity.com/vla/generalist-vla-models-and-benchmarks/)
- Mechanistic interpretability / [Steering and probing for LLM safety](https://mlsanity.com/mechinterp/steering-and-probing-for-llm-safety/)

## Builds on (most cited first, 27 of 27)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [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)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders](https://mlsanity.com/paper/2409.14507/) (2024)
- [Analyzing Transformers in Embedding Space](https://mlsanity.com/paper/2209.02535/) (2022)
- [BatchTopK Sparse Autoencoders](https://mlsanity.com/paper/2412.06410/) (2024)
- [Towards Interpreting Visual Information Processing in Vision-Language Models](https://mlsanity.com/paper/2410.07149/) (2024)
- [Automatically Interpreting Millions of Features in Large Language Models](https://mlsanity.com/paper/2410.13928/) (2024)
- [A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models](https://mlsanity.com/paper/2503.05613/) (2025)
- [Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models](https://mlsanity.com/paper/2504.02821/) (2025)
- [Waypoint-Based Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2307.14326/) (2023)
- [Interpreting the linear structure of vision-language model embedding spaces](https://mlsanity.com/paper/2504.11695/) (2025)
- [Mechanistic interpretability for steering vision-language-action models](https://mlsanity.com/paper/2509.00328/) (2025)
- [The Utility of Explainable AI in Ad Hoc Human-Machine Teaming](https://mlsanity.com/paper/2209.03943/) (2022)
- [When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs](https://mlsanity.com/paper/2602.17659/) (2026)
- [SAE-V: Interpreting Multimodal Models for Enhanced Alignment](https://mlsanity.com/paper/2502.17514/) (2025)
- [Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs](https://mlsanity.com/paper/2411.19187/) (2024)
- [Observing and Controlling Features in Vision-Language-Action Models](https://mlsanity.com/paper/2603.05487/) (2026)
- [Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models](https://mlsanity.com/paper/2603.19183/) (2026)
- [Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models](https://mlsanity.com/paper/2603.19233/) (2026)
- [Learning Interpretable, High-Performing Policies for Autonomous Driving](https://mlsanity.com/paper/2202.02352/) (2022)

## Built on by (most cited first, 2 of 2)

- [IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Trajectories for Vision-Language-Action Policies](https://mlsanity.com/paper/2609.15005/) (2026)
- [Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models](https://mlsanity.com/paper/2610.03498/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and vision-language models do not transfer cleanly to VLAs: outputs are robot actions rather than human-readable tokens, and interventions can only be tested via expensive closed-loop rollouts. We propose an event-grounded interpretability pipeline that anchors SAE feature analysis to behavioral events rather than text contexts. End-effector keyframes are clustered within each task using visual, state, and temporal cues, linking SAE features to behaviorally salient events and, via optional VLM annotations, to semantic context. To our knowledge, our pipeline is among the first to ground SAE-based VLA analysis in closed-loop behavioral events. Across two simulation architectures and a real-robot study, event-grounded ranking yields the strongest causal effects on OpenVLA and transfers to the continuous action chunks of π0.5. SAE is a sparse but imperfect intervention basis: usability varies with architecture and intervention site, and aggressive intervention reveals safety and interpretability limits. Overall, event-grounded SAE analysis emerges as a practical starting point for behavior-anchored VLA interpretability, motivating future work on SAE features beyond action-aligned coordinates, finer-grained closed-loop evaluation, and safe interventions for high-stakes VLA deployments. Code is available at urlhttps://github.com/xc-j/Event-SAE.