Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98295
    Prev
    Next
    INDEX
    Explanations

    主

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    打
    -0.09
    of
    -0.08
    打法
    -0.08
    turn
    -0.08
    Military
    -0.08
     demol
    -0.08
    Of
    -0.07
     Of
    -0.07
    Prize
    -0.07
     Military
    -0.07
    POSITIVE LOGITS
    观
    0.13
    觀
    0.13
    観
    0.11
    观看
    0.11
    관
    0.11
     관
    0.10
    觀看
    0.10
    體
    0.09
    体
    0.09
    체
    0.09
    Activations Density 0.001%

    No Known Activations