© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54437
    Prev
    Next
    INDEX
    Explanations

    reflective

    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
    anze
    -0.08
    altime
    -0.08
     planos
    -0.07
    Tenant
    -0.07
     télévision
    -0.07
     массов
    -0.07
     previstos
    -0.07
     KT
    -0.07
    980
    -0.07
     ROC
    -0.07
    POSITIVE LOGITS
     bim
    0.08
    िरोध
    0.08
    ening
    0.08
     वाह
    0.08
     xar
    0.08
    ym
    0.08
     चम
    0.08
    ened
    0.08
     inflamm
    0.08
     exch
    0.08
    Activations Density 0.002%

    No Known Activations