© 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. 78173
    Prev
    Next
    INDEX
    Explanations

    bridge

    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
    िक
    -0.09
     संस्क
    -0.08
    \Models
    -0.07
     preprocess
    -0.07
    icient
    -0.07
    incip
    -0.07
     בינ
    -0.07
     यांनी
    -0.07
     among
    -0.07
     participant
    -0.07
    POSITIVE LOGITS
     спокойно
    0.08
     جميل
    0.07
     enlist
    0.07
     начин
    0.07
    дя
    0.07
    _plural
    0.07
     stolz
    0.07
     دستور
    0.07
     дороги
    0.07
    ATR
    0.07
    Activations Density 0.006%

    No Known Activations