© 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. 47293
    Prev
    Next
    INDEX
    Explanations

    解决

    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
     kilometer
    -0.09
     conson
    -0.09
     breeders
    -0.09
    uly
    -0.08
     Kilometer
    -0.08
     perhatian
    -0.08
    খ্য
    -0.08
     הזמן
    -0.08
    ಂತ
    -0.08
    特徴
    -0.08
    POSITIVE LOGITS
     VMware
    0.10
     painel
    0.09
     diagno
    0.09
     troubleshooting
    0.09
     диагности
    0.08
    解决
    0.08
    smtp
    0.08
     diagnostic
    0.08
    _win
    0.08
     soluciones
    0.08
    Activations Density 0.074%

    No Known Activations