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. 19097
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ,所以
    -0.09
    ?↵↵
    -0.08
     something
    -0.07
    。所以
    -0.07
    -resource
    -0.07
    _op
    -0.07
    ,"
    -0.07
    _code
    -0.07
    -context
    -0.07
     code
    -0.07
    POSITIVE LOGITS
     glossy
    0.09
     включая
    0.09
     uitgerust
    0.09
     Featuring
    0.09
     ففي
    0.08
     écht
    0.08
     วิ
    0.08
     พร้อม
    0.08
     หนัง
    0.08
     καθώς
    0.08
    Activations Density 0.005%

    No Known Activations