© 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. 7607
    Prev
    Next
    INDEX
    Explanations

    wrote

    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
     위한
    -0.08
     Chairs
    -0.08
    _walk
    -0.08
     المنزل
    -0.08
    လို
    -0.07
    iro
    -0.07
    raham
    -0.07
    ಗಾಗಿ
    -0.07
     ਲਈ
    -0.07
    ilever
    -0.07
    POSITIVE LOGITS
    ว่า
    0.10
     bop
    0.09
     "(
    0.09
     bold
    0.09
     "".
    0.08
    geri
    0.07
     Đông
    0.07
     yor
    0.07
     ότι
    0.07
     dash
    0.07
    Activations Density 0.012%

    No Known Activations