© 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. 129403
    Prev
    Next
    INDEX
    Explanations

    People

    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
     pai
    -0.08
     Eleg
    -0.08
     приказ
    -0.08
     Вы
    -0.07
     трах
    -0.07
    Eleg
    -0.07
     Triumph
    -0.07
     compt
    -0.07
    announce
    -0.07
     quinto
    -0.07
    POSITIVE LOGITS
     niile
    0.10
    들에게
    0.09
     individus
    0.09
     beings
    0.09
    们
    0.09
    行为
    0.09
     számára
    0.08
    들이
    0.08
    々
    0.08
    主动
    0.08
    Activations Density 0.073%

    No Known Activations