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. 65765
    Prev
    Next
    INDEX
    Explanations

    navigation

    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
    marshal
    -0.09
    otlin
    -0.09
     soli
    -0.08
    409
    -0.08
    epoch
    -0.08
    Cpf
    -0.08
     Jenner
    -0.08
    Certificate
    -0.07
    Constraint
    -0.07
     squeezing
    -0.07
    POSITIVE LOGITS
     меню
    0.18
    菜单
    0.17
     메뉴
    0.16
     menú
    0.16
    _MENU
    0.16
     Menu
    0.16
     MENU
    0.15
     menu
    0.15
    -menu
    0.15
    .Menu
    0.15
    Activations Density 0.042%

    No Known Activations