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. 56104
    Prev
    Next
    INDEX
    Explanations

    log

    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
     governs
    -0.09
     syllabus
    -0.09
     Gover
    -0.08
    برنامج
    -0.08
     Frauen
    -0.08
    forces
    -0.08
    -0.08
     grasp
    -0.08
    下載
    -0.07
     Bonn
    -0.07
    POSITIVE LOGITS
    .Logger
    0.14
    .log
    0.13
     লগ
    0.12
    日志
    0.12
    .warn
    0.12
     logging
    0.12
     로그
    0.12
    (logging
    0.11
     logger
    0.11
    =logging
    0.11
    Activations Density 0.009%

    No Known Activations