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. 30687
    Prev
    Next
    INDEX
    Explanations

    **

    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
     capp
    -0.09
    趋
    -0.08
     obsessive
    -0.08
     Fool
    -0.08
    拍
    -0.08
    iais
    -0.08
     huwelijk
    -0.08
     OPS
    -0.08
     imp
    -0.08
     Pope
    -0.08
    POSITIVE LOGITS
    ರ್ವ
    0.08
     сущ
    0.07
     الوس
    0.07
     Это
    0.07
     hierfür
    0.07
     erb
    0.07
     essence
    0.07
     wi
    0.07
     _(
    0.07
     이에
    0.07
    Activations Density 0.054%

    No Known Activations