Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9154
    Prev
    Next
    INDEX
    Explanations

    Comma

    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
     connus
    -0.08
     staats
    -0.07
     angekommen
    -0.07
    Military
    -0.07
     ప్రభుత్వ
    -0.07
     courts
    -0.07
    -0.07
    ਾਇ
    -0.07
    .runtime
    -0.07
     receptive
    -0.07
    POSITIVE LOGITS
    stäl
    0.09
     przeciw
    0.09
     ЕС
    0.08
     ESC
    0.08
     写
    0.08
     シャ
    0.08
    bang
    0.08
     YOU
    0.08
    �్
    0.08
     DAN
    0.08
    Activations Density 0.048%

    No Known Activations