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. 106237
    Prev
    Next
    INDEX
    Explanations

    code and logs

    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
     מוכ
    -0.09
    genwoord
    -0.09
     пласт
    -0.08
     граждан
    -0.08
     বস
    -0.08
    ɔn
    -0.08
     chinhu
    -0.08
     compromiso
    -0.08
     nominate
    -0.08
     berlaku
    -0.08
    POSITIVE LOGITS
    日志
    0.13
     logs
    0.13
     logfile
    0.13
    Logs
    0.13
    ログ
    0.12
    _logs
    0.12
    .log
    0.11
    Log
    0.11
     log
    0.11
     로그
    0.11
    Activations Density 0.011%

    No Known Activations