© 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. 29506
    Prev
    Next
    INDEX
    Explanations

    Puzzles

    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
    職
    -0.08
     pensions
    -0.08
    退休
    -0.08
     handige
    -0.08
     peek
    -0.08
     stroller
    -0.08
     retirees
    -0.08
     Retirement
    -0.08
    予定
    -0.08
    $str
    -0.07
    POSITIVE LOGITS
     правильно
    0.09
     somehow
    0.08
     sorgfält
    0.08
     improb
    0.08
     Alone
    0.08
     urgently
    0.08
    仪
    0.08
     cuidadosamente
    0.08
     EXACT
    0.08
     alone
    0.08
    Activations Density 0.034%

    No Known Activations