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. 120454
    Prev
    Next
    INDEX
    Explanations

    type

    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
     Shoulder
    -0.08
     shoulder
    -0.08
    .Center
    -0.07
     assault
    -0.07
     gond
    -0.07
     Anthem
    -0.07
    .Super
    -0.07
     Cardinals
    -0.07
     trium
    -0.07
    ạnh
    -0.07
    POSITIVE LOGITS
     ಗ
    0.08
     CEL
    0.08
     CDI
    0.08
     Crow
    0.08
     Einwohner
    0.08
    crow
    0.08
    _python
    0.08
     cds
    0.08
     WIB
    0.07
    이지
    0.07
    Activations Density 0.001%

    No Known Activations