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. 60924
    Prev
    Next
    INDEX
    Explanations

    comparisons of small values

    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
    Df
    -0.09
    richt
    -0.08
    मन
    -0.08
     Frieden
    -0.08
     Patterson
    -0.07
    oretical
    -0.07
     dysfunction
    -0.07
    issé
    -0.07
    .rc
    -0.07
    онах
    -0.07
    POSITIVE LOGITS
     الحجم
    0.09
     규모
    0.09
     बाकी
    0.09
     Ratio
    0.08
    比例
    0.08
    规模
    0.08
    ỉ
    0.08
    իայի
    0.08
     aby
    0.08
    cí
    0.08
    Activations Density 0.006%

    No Known Activations