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. 58960
    Prev
    Next
    INDEX
    Explanations

    document titles

    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
     salvo
    -0.09
     pola
    -0.09
     porr
    -0.08
     cuál
    -0.08
     che
    -0.08
     kiam
    -0.08
     pollo
    -0.08
     sre
    -0.08
     Reservoir
    -0.08
     florida
    -0.07
    POSITIVE LOGITS
     搜
    0.09
     使用
    0.08
    _SETTING
    0.08
    requires
    0.08
    tons
    0.07
     מדובר
    0.07
    ved
    0.07
     inzicht
    0.07
     dirname
    0.07
     using
    0.07
    Activations Density 0.115%

    No Known Activations