© 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. 3-RESID-POST-AA
    11. 2714
    Prev
    Next
    INDEX
    Explanations

    initialize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಗಾರ
    -0.08
     Sunda
    -0.08
     orang
    -0.07
     кай
    -0.07
     Soleil
    -0.07
    refix
    -0.07
    -0.07
     siy
    -0.07
     oro
    -0.07
     रास्त
    -0.07
    POSITIVE LOGITS
    ilise
    0.08
    ialize
    0.08
     شدن
    0.08
     nang
    0.08
    ierung
    0.07
    IATE
    0.07
    itate
    0.07
     Domingo
    0.07
    itialize
    0.07
    693
    0.07
    Activations Density 0.013%
    No Known Activations