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. 112992
    Prev
    Next
    INDEX
    Explanations

    hospital

    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
    ಚ್
    -0.08
     truy
    -0.08
     Pond
    -0.08
    ujesz
    -0.08
    Champ
    -0.07
    তিক
    -0.07
    KC
    -0.07
     सौ
    -0.07
     Rasmussen
    -0.07
     chwil
    -0.07
    POSITIVE LOGITS
     Harriet
    0.08
     Agnes
    0.08
    .Args
    0.07
     Raymond
    0.07
     inaugurated
    0.07
     precip
    0.07
     интерес
    0.07
    -ac
    0.07
     Cros
    0.07
     ges
    0.07
    Activations Density 0.010%

    No Known Activations