© 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. 54476
    Prev
    Next
    INDEX
    Explanations

    better

    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
    ীয়
    -0.08
    මු
    -0.08
     Hedge
    -0.07
     가지
    -0.07
    -0.07
    ীদ
    -0.07
     rejecting
    -0.07
     번째
    -0.07
     taş
    -0.07
    대를
    -0.07
    POSITIVE LOGITS
     improvement
    0.18
     improvements
    0.16
    改善
    0.16
     Improvement
    0.15
     개선
    0.15
     સુધ
    0.14
     Improvements
    0.13
     improves
    0.13
     worsening
    0.13
     melhorias
    0.13
    Activations Density 0.062%
    No Known Activations