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. 30635
    Prev
    Next
    INDEX
    Explanations

    variant

    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
     cip
    -0.09
     choose
    -0.08
     персона
    -0.07
    701
    -0.07
     linea
    -0.07
     Cait
    -0.07
     ಸಂಪರ್ಕ
    -0.07
     CGI
    -0.07
     costume
    -0.07
     recogn
    -0.07
    POSITIVE LOGITS
     pior
    0.08
    fname
    0.08
     usp
    0.08
     Ritual
    0.08
     fjöl
    0.08
    osaurs
    0.08
    vl
    0.07
     tende
    0.07
    ôs
    0.07
     удар
    0.07
    Activations Density 0.001%

    No Known Activations