© 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. 24612
    Prev
    Next
    INDEX
    Explanations

    inside

    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
     retirement
    -0.08
    נהל
    -0.08
    leistung
    -0.08
    =======↵
    -0.08
    Stake
    -0.07
     sexual
    -0.07
    =index
    -0.07
     Dev
    -0.07
     ưu
    -0.07
     retail
    -0.07
    POSITIVE LOGITS
    halb
    0.10
     Djokovic
    0.08
    ward
    0.07
     kter
    0.07
    ellig
    0.07
     subtract
    0.07
    -but
    0.07
     escritura
    0.07
    zy
    0.07
    Contours
    0.07
    Activations Density 0.016%

    No Known Activations