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. 102996
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    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
    اك
    -0.08
     pelea
    -0.08
     woman's
    -0.08
     particularmente
    -0.08
    ாவில்
    -0.08
    ٽي
    -0.07
    Liverpool
    -0.07
     Batter
    -0.07
     peek
    -0.07
    _ZERO
    -0.07
    POSITIVE LOGITS
    (Delete
    0.09
     imprint
    0.08
     löschen
    0.08
    ardown
    0.08
     삭제
    0.08
     删除
    0.08
    删除
    0.08
    _delete
    0.07
     sculpt
    0.07
     syl
    0.07
    Activations Density 0.004%

    No Known Activations