Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49272
    Prev
    Next
    INDEX
    Explanations

    found

    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
     Industrial
    -0.08
     суток
    -0.08
     promo
    -0.07
    чика
    -0.07
    ್ದ
    -0.07
    דרך
    -0.07
     Seek
    -0.07
    ्त
    -0.07
     drawable
    -0.07
     transferring
    -0.07
    POSITIVE LOGITS
     bahwa
    0.09
    全文
    0.09
     fenn
    0.08
     कि
    0.08
     shir
    0.08
    Violation
    0.08
     ukuthi
    0.08
     oti
    0.08
     saut
    0.08
     Chir
    0.08
    Activations Density 0.032%

    No Known Activations