Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102926
    Prev
    Next
    INDEX
    Explanations

    diagrams/code

    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
    験
    -0.09
    QD
    -0.08
    措
    -0.08
     Breda
    -0.08
     öner
    -0.08
    QT
    -0.08
    ਾਉ
    -0.08
     vhod
    -0.08
    ாண்ட
    -0.08
     attent
    -0.08
    POSITIVE LOGITS
     podr
    0.08
    Nach
    0.08
     Where
    0.07
     Pag
    0.07
     arrow
    0.07
     Arrow
    0.07
     Arena
    0.07
     Icons
    0.07
     Outs
    0.07
     Nach
    0.07
    Activations Density 0.010%

    No Known Activations