© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47805
    Prev
    Next
    INDEX
    Explanations

    filled

    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
     Ech
    -0.08
     assimilation
    -0.08
    (cancel
    -0.07
    ough
    -0.07
    periode
    -0.07
     epidemi
    -0.07
     suw
    -0.07
    irer
    -0.07
    DC
    -0.07
    _USERNAME
    -0.07
    POSITIVE LOGITS
     closet
    0.09
    helves
    0.09
     তাক
    0.08
    ร้าน
    0.08
     iā
    0.08
     объем
    0.08
     bookshelf
    0.08
     φυσ
    0.08
    fis
    0.08
     шкаф
    0.08
    Activations Density 0.003%

    No Known Activations