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. 12992
    Prev
    Next
    INDEX
    Explanations

    fossil fuels

    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
    UC
    -0.08
     ঘ
    -0.07
    Co
    -0.07
    LS
    -0.07
    Constraint
    -0.07
    Ver
    -0.07
     থাকার
    -0.07
    Paris
    -0.07
    所在
    -0.07
    constraint
    -0.07
    POSITIVE LOGITS
     Sgt
    0.09
    genoten
    0.08
     Amount
    0.08
    _FACTORY
    0.08
    HEET
    0.08
    िटल
    0.08
    ээн
    0.08
    'aur
    0.08
     IDictionary
    0.08
     Bitcoins
    0.08
    Activations Density 0.001%

    No Known Activations