© 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. 108737
    Prev
    Next
    INDEX
    Explanations

    answer

    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
     simplicity
    -0.08
     payoff
    -0.08
     Kling
    -0.08
    -0.08
     extr
    -0.08
     parentheses
    -0.07
     จ
    -0.07
    !!
    -0.07
     Geh
    -0.07
     плод
    -0.07
    POSITIVE LOGITS
     ngeunaan
    0.09
     momba
    0.09
     dotyczą
    0.08
     informacji
    0.08
    صار
    0.07
     बारे
    0.07
     articulated
    0.07
     tentang
    0.07
     kim
    0.07
     pili
    0.07
    Activations Density 0.021%
    No Known Activations