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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29897
    Prev
    Next
    INDEX
    Explanations

    Kawasaki

    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
    й
    -0.09
    _refresh
    -0.08
    loaded
    -0.08
    hot
    -0.08
    _loaded
    -0.07
    eg
    -0.07
    teste
    -0.07
    refresh
    -0.07
     Refresh
    -0.07
    刷新
    -0.07
    POSITIVE LOGITS
     Του
    0.08
     comerciantes
    0.08
     enam
    0.08
     Bres
    0.08
    insic
    0.08
     đủ
    0.08
    结果
    0.07
     ထ
    0.07
    邻
    0.07
     sonucu
    0.07
    Activations Density 0.000%

    No Known Activations