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. 55936
    Prev
    Next
    INDEX
    Explanations

    Year 2100 climate predictions

    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
     opinions
    -0.07
     하고
    -0.07
     인정
    -0.07
     grava
    -0.07
     �
    -0.07
     awards
    -0.07
     ರಾಷ್ಟ್ರೀಯ
    -0.07
    诈
    -0.07
    认为
    -0.07
     하면
    -0.07
    POSITIVE LOGITS
    'arrêt
    0.08
    -mile
    0.08
    _STAR
    0.08
    -år
    0.08
    .Guid
    0.08
     Lansing
    0.08
     Carn
    0.08
    ပ္
    0.08
    ’arrêt
    0.08
    insdag
    0.07
    Activations Density 0.003%

    No Known Activations