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. 58463
    Prev
    Next
    INDEX
    Explanations

    5 or 7

    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
    资
    -0.08
     finales
    -0.08
     Ginn
    -0.07
     kesin
    -0.07
     Benson
    -0.07
     glean
    -0.07
    Kyle
    -0.07
     hypothesis
    -0.07
     mike
    -0.07
    综合
    -0.07
    POSITIVE LOGITS
     kaw
    0.09
    ég
    0.08
     lac
    0.08
    เครื่อง
    0.07
    clock
    0.07
     Sarat
    0.07
     plas
    0.07
     CF
    0.07
     quarter
    0.07
     moun
    0.07
    Activations Density 0.011%

    No Known Activations