© 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. 99129
    Prev
    Next
    INDEX
    Explanations

    statistical calculations

    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
     diverse
    -0.08
    Agg
    -0.08
     sé
    -0.08
    iera
    -0.07
     devices
    -0.07
     Immun
    -0.07
    .ag
    -0.07
    borg
    -0.07
     Agg
    -0.07
     dry
    -0.07
    POSITIVE LOGITS
     akan
    0.10
    iriman
    0.08
     çift
    0.08
     withdrawing
    0.08
     yorum
    0.08
     deram
    0.08
     recess
    0.08
     blong
    0.08
    وقف
    0.08
     двумя
    0.08
    Activations Density 0.002%

    No Known Activations