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. 15-RESID-POST-AA
    6. 140
    Prev
    Next
    INDEX
    Explanations

    of

    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
    flare
    -0.08
    lated
    -0.07
    meal
    -0.07
    compiler
    -0.07
     calloc
    -0.07
    Earlier
    -0.07
     Hoge
    -0.07
    ("",
    -0.07
    Compiler
    -0.07
    -0.07
    POSITIVE LOGITS
     squared
    0.10
     elusive
    0.10
    叶
    0.08
     숨
    0.08
    ابة
    0.08
    شرق
    0.08
    长度
    0.08
    圆
    0.07
     satisfy
    0.07
    钱
    0.07
    Activations Density 0.021%

    No Known Activations