© 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. 30930
    Prev
    Next
    INDEX
    Explanations

    infinity

    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
    ге
    -0.08
     NZ
    -0.08
     UM
    -0.07
    기간
    -0.07
     sweets
    -0.07
     undertaken
    -0.07
     bumps
    -0.07
    밀
    -0.07
     contention
    -0.07
    /inter
    -0.07
    POSITIVE LOGITS
     negativo
    0.09
     البيان
    0.09
     xuống
    0.08
     dhig
    0.08
     يدخل
    0.08
     صور
    0.08
    =-
    0.08
    Offline
    0.08
     unfavorable
    0.08
     negativity
    0.08
    Activations Density 0.008%

    No Known Activations