© 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. 74
    Prev
    Next
    INDEX
    Explanations

    screen mirroring

    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
     часов
    -0.09
     heure
    -0.08
     местах
    -0.08
    &returns
    -0.08
    гүз
    -0.08
    lygyny
    -0.08
     кунанд
    -0.08
    utany
    -0.08
    lygy
    -0.07
    manha
    -0.07
    POSITIVE LOGITS
     Petersen
    0.08
     Gibbs
    0.08
     Yeah
    0.07
     Valencia
    0.07
    136
    0.07
     prisoner
    0.07
     weder
    0.07
     summon
    0.07
    れば
    0.07
    itored
    0.07
    Activations Density 0.000%

    No Known Activations