© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102900
    Prev
    Next
    INDEX
    Explanations

    unlocking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _session
    -0.08
     আন্দোল
    -0.08
     berger
    -0.07
     Crud
    -0.07
     sobra
    -0.07
     mouvement
    -0.07
     sıcak
    -0.07
     Cush
    -0.07
     cushion
    -0.07
     giovani
    -0.07
    POSITIVE LOGITS
     unlock
    0.33
     unlocking
    0.33
     desblo
    0.32
     unlocked
    0.32
    Unlock
    0.32
     Unlock
    0.32
    unlock
    0.30
    _unlock
    0.29
    .unlock
    0.29
    Unlocked
    0.28
    Activations Density 0.068%

    No Known Activations