© 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. 44676
    Prev
    Next
    INDEX
    Explanations

    communication requests

    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
    llt
    -0.08
     Powerful
    -0.08
     egy
    -0.08
    .Must
    -0.07
    imbawa
    -0.07
     invented
    -0.07
     immoral
    -0.07
     phải
    -0.07
     politicians
    -0.07
    must
    -0.07
    POSITIVE LOGITS
     pihak
    0.09
     sincerely
    0.09
    uestras
    0.08
    րս
    0.08
    RESULT
    0.08
     kwest
    0.08
     Anliegen
    0.08
     رد
    0.08
     পক্ষ
    0.08
     pest
    0.08
    Activations Density 0.057%

    No Known Activations