© 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. 1045
    Prev
    Next
    INDEX
    Explanations

    Feeding

    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
    自身
    -0.09
     स्वत
    -0.08
    पूर्ण
    -0.08
    退出
    -0.07
    िकी
    -0.07
     propios
    -0.07
    orst
    -0.07
    mé
    -0.07
     abb
    -0.07
     dibuat
    -0.07
    POSITIVE LOGITS
     ಆಹ
    0.09
     ഭക്ഷ
    0.09
     oatmeal
    0.08
     frightened
    0.08
     chăm
    0.08
     regularmente
    0.08
     feeding
    0.08
     weekly
    0.08
     feeder
    0.08
     Betreuung
    0.08
    Activations Density 0.035%

    No Known Activations