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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 49566
    Prev
    Next
    INDEX
    Explanations

    "result" in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يدخل
    -0.07
    -0.07
    aggable
    -0.06
    ijkstra
    -0.06
    ibold
    -0.06
    adeiras
    -0.06
    ABLED
    -0.06
    aham
    -0.06
    andag
    -0.06
    �ร
    -0.06
    POSITIVE LOGITS
    结果
    0.74
    結果
    0.73
     결과
    0.71
     résultats
    0.70
     resultados
    0.70
     પરિણામ
    0.70
     परिणाम
    0.69
     résultat
    0.68
     резул
    0.67
     result
    0.66
    Activations Density 0.920%
    No Known Activations