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. 53894
    Prev
    Next
    INDEX
    Explanations

    slope

    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
     hilar
    -0.09
     arth
    -0.08
     welfare
    -0.08
     Mais
    -0.07
     intens
    -0.07
     Sunni
    -0.07
     Hiroshima
    -0.07
     electromagnetic
    -0.07
     massif
    -0.07
     Tears
    -0.07
    POSITIVE LOGITS
    是多少
    0.09
    =-
    0.08
     mola
    0.07
     jumped
    0.07
    :-
    0.07
     despre
    0.07
    iciente
    0.07
    icy
    0.07
     chic
    0.07
     pencil
    0.07
    Activations Density 0.012%

    No Known Activations