© 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. 30189
    Prev
    Next
    INDEX
    Explanations

    time and local time

    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
     entrepr
    -0.08
     chống
    -0.08
    创业
    -0.08
     maara
    -0.08
     purse
    -0.08
     reliance
    -0.08
     signaling
    -0.07
    quit
    -0.07
    _bid
    -0.07
    -sur
    -0.07
    POSITIVE LOGITS
     terrestre
    0.09
    Temps
    0.09
     Temps
    0.08
    转换
    0.08
     terrest
    0.08
    (local
    0.08
    (convert
    0.08
     Vorte
    0.07
     Converts
    0.07
    ilegt
    0.07
    Activations Density 0.003%

    No Known Activations