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. 12791
    Prev
    Next
    INDEX
    Explanations

    polynomial

    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
    .NON
    -0.08
     Stras
    -0.08
    幸福
    -0.07
     prospects
    -0.07
    -thumbnail
    -0.07
     équipements
    -0.07
    otti
    -0.07
    .avatar
    -0.07
     الأولى
    -0.07
     personnels
    -0.07
    POSITIVE LOGITS
     polynomial
    0.11
    Polynomial
    0.09
     Polynomial
    0.09
    мис
    0.09
    ynomials
    0.09
    ynomial
    0.08
     explode
    0.08
    লার
    0.08
    шую
    0.08
    дап
    0.08
    Activations Density 0.022%

    No Known Activations