© 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. 8000
    Prev
    Next
    INDEX
    Explanations

    grinding

    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
    mitt
    -0.08
    luent
    -0.08
    Shell
    -0.08
    Det
    -0.08
    bill
    -0.08
    35
    -0.07
    ivit
    -0.07
     Telef
    -0.07
    wise
    -0.07
    prim
    -0.07
    POSITIVE LOGITS
     clen
    0.09
     sonrisa
    0.09
     silently
    0.09
     কব
    0.08
     swords
    0.08
     anguish
    0.08
     grin
    0.08
    יניים
    0.08
     Teeth
    0.08
     Martial
    0.08
    Activations Density 0.004%

    No Known Activations