claim
active
claim:intractable-does-not-mean-unrecoverable-a-direction-the-safety-tuned-base-resists-exposing-can-still-be-estimated-from-a-less-safe-relative

Intractable does not mean unrecoverable: a direction the safety-tuned base resists exposing can still be estimated from a less-safe relative

Demonstrated through the evil-vector transfer from AMORAL-GPT-OSS into unmodified G20B

Source paper

extracted_from
What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors
(2026) · Winston Zeng · Ali Emami · J H Choi

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.