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. 58515
    Prev
    Next
    INDEX
    Explanations

    Between-group variance calculations

    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
     米
    -0.08
    -eng
    -0.08
    ומר
    -0.08
    687
    -0.08
     emoção
    -0.08
     постав
    -0.07
    \(
    -0.07
    726
    -0.07
    #↵↵
    -0.07
     Gabriel
    -0.07
    POSITIVE LOGITS
     Wahl
    0.08
     kracht
    0.08
    宏
    0.08
    hosts
    0.08
     sâu
    0.08
     bulls
    0.08
     negligible
    0.08
     sobres
    0.07
    ကြ
    0.07
     चयन
    0.07
    Activations Density 0.004%

    No Known Activations