Activation Steering Transfer to Agents: One Gain Ratio Does Not Identify Potency and Efficacy
Additive activation steering is calibrated in single-turn chat, then deployed inside agent scaffolds. The quantity usually reported for that move is a gain: a ratio of steered effects, T = Delta_agent / Delta_chat. We sweep eight family x arm dose-response cells over six models in both deployment contexts and show this ratio does not identify potency and efficacy. Reconstructing the published estimator in both of its forms on our own grids, its realized range contains 1 in five of five scorable cells, it moves with dose in four of five, and two cells with opposite potency shifts, both CI-clean on the primary grid, return gain intervals overlapping at a width under 0.08. Every scorable cel...
| Authors | Lucas Pinto |
|---|---|
| Primary category | cs.LG |
| Published | 10 July 2026 |
| Last updated at source | 29 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.