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. 106109
    Prev
    Next
    INDEX
    Explanations

    options

    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
    ματο
    -0.07
     indis
    -0.07
    -0.07
    Lam
    -0.07
     lam
    -0.07
    .reshape
    -0.07
     layout
    -0.07
    -0.07
     LS
    -0.07
    attar
    -0.07
    POSITIVE LOGITS
    订
    0.10
    竞彩足球
    0.08
     Hague
    0.08
     Sommer
    0.08
    ,比
    0.08
     หุ้น
    0.08
     adjunct
    0.08
     Holdings
    0.08
     جماعت
    0.08
     Hawks
    0.07
    Activations Density 0.002%

    No Known Activations