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. 15-RESID-POST-AA
    6. 19412
    Prev
    Next
    INDEX
    Explanations

    calculating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    کړ
    -0.09
    NIEnv
    -0.08
     cref
    -0.08
     virtuelle
    -0.08
    ENAME
    -0.08
    APR
    -0.08
     telle
    -0.08
    ename
    -0.08
    holders
    -0.08
    ever
    -0.07
    POSITIVE LOGITS
    ميم
    0.09
    sell
    0.08
    milk
    0.08
    rent
    0.08
    76
    0.08
    স্থ
    0.07
    স্থান
    0.07
    दाता
    0.07
    kos
    0.07
    212
    0.07
    Activations Density 0.155%

    No Known Activations