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

    Neuronpedia

    APICircuit 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. 60828
    Prev
    Next
    INDEX
    Explanations

    kin

    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
     тол
    -0.08
     sorg
    -0.07
     dol
    -0.07
     Mehr
    -0.07
     neu
    -0.07
     Australia's
    -0.07
    Quel
    -0.07
     Beled
    -0.07
     forza
    -0.07
     faszin
    -0.07
    POSITIVE LOGITS
     habitual
    0.09
     gloves
    0.09
     contenant
    0.09
    -lined
    0.09
     রেখে
    0.08
     tucked
    0.08
    夹
    0.08
    аб
    0.08
     cracked
    0.07
     dab
    0.07
    Activations Density 0.003%

    No Known Activations