© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68171
    Prev
    Next
    INDEX
    Explanations

    random text

    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
     biomarkers
    -0.09
     sexy
    -0.08
     yogurt
    -0.08
    -bottom
    -0.08
    $('#
    -0.08
     PREMIUM
    -0.08
     announced
    -0.07
     drogas
    -0.07
     duer
    -0.07
    /pre
    -0.07
    POSITIVE LOGITS
     historically
    0.27
     historical
    0.26
    Historical
    0.24
     Historically
    0.24
    历史
    0.23
     historic
    0.23
     histó
    0.23
     historische
    0.23
     Historical
    0.23
     histórica
    0.22
    Activations Density 0.607%

    No Known Activations