© 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. 95382
    Prev
    Next
    INDEX
    Explanations

    sentence or line

    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
    _raw
    -0.08
    meet
    -0.07
     celui
    -0.07
    Raw
    -0.07
     totes
    -0.07
     meets
    -0.07
    ategory
    -0.07
     lectures
    -0.07
    /raw
    -0.07
     এব
    -0.07
    POSITIVE LOGITS
    一句
    0.09
    -Benz
    0.09
     сформ
    0.09
    ાઓ
    0.08
     מתוך
    0.08
     liners
    0.08
     Linking
    0.08
    benz
    0.08
     acknow
    0.08
    (s
    0.08
    Activations Density 0.065%

    No Known Activations