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. 49861
    Prev
    Next
    INDEX
    Explanations

    екст

    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
     heridas
    -0.09
    加
    -0.08
     gobern
    -0.08
    ,加
    -0.08
     unterstützen
    -0.08
     Bren
    -0.08
    emann
    -0.08
    ציע
    -0.08
     bala
    -0.08
     recursos
    -0.08
    POSITIVE LOGITS
     rehears
    0.08
    filesystem
    0.07
    \\/
    0.07
     жол
    0.07
    _Custom
    0.07
    0.07
    /R
    0.07
    ETE
    0.07
     filesystem
    0.07
    .Black
    0.07
    Activations Density 0.073%

    No Known Activations