Editing the Goal: Per-Token SAE Steering and Its Depth Limits in pi 0.5

arXiv:2611.00602 · cs.AI · Submitted 2026-10-31 · Read on arXiv

cs.AI

Submitted: 2026-10-31

Updated: 2026-10-31

Comments: Accepted to the Science of Physical AI Safety (SPAIS) Workshop at CoRL 2026. 6 pages, 2 figures

Code: https://github.com/Physical-Intelligence/openpi

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers