© 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. 11-RESID-POST-AA
    11. 78839
    Prev
    Next
    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hitter
    -0.08
     abused
    -0.08
     HGH
    -0.08
     judi
    -0.08
    алау
    -0.08
     والح
    -0.08
     largest
    -0.08
     الصح
    -0.08
     punches
    -0.07
     الصحيح
    -0.07
    POSITIVE LOGITS
     ವ್ಯಕ್ತ
    0.08
    represented
    0.08
    semantic
    0.07
    phants
    0.07
    phant
    0.07
     Midland
    0.07
    _Menu
    0.07
    ?)
    0.07
     smells
    0.07
    leaders
    0.07
    Activations Density 0.007%

    No Known Activations