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. 12813
    Prev
    Next
    INDEX
    Explanations

    knowledge cutoff dates

    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
    chner
    -0.08
     presentatie
    -0.08
    preci
    -0.08
    Equation
    -0.07
    漂亮
    -0.07
     bitch
    -0.07
     annoying
    -0.07
     tack
    -0.07
    antz
    -0.07
     outright
    -0.07
    POSITIVE LOGITS
    OCR
    0.09
     नवंबर
    0.09
     OCR
    0.09
     ACCESS
    0.08
    截至
    0.08
     '{
    0.08
     접근
    0.08
     अक्टूबर
    0.08
     Zugriff
    0.08
     सितंबर
    0.08
    Activations Density 0.008%

    No Known Activations