© 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. 99505
    Prev
    Next
    INDEX
    Explanations

    translation

    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
    pev
    -0.07
    aysay
    -0.07
     Euras
    -0.07
     deaktiv
    -0.07
     நிகழ
    -0.07
     yapı
    -0.07
     Wunder
    -0.07
    .obs
    -0.07
    Playback
    -0.07
     Richter
    -0.07
    POSITIVE LOGITS
     capita
    0.09
     futuras
    0.07
     তা
    0.07
    ınd
    0.07
    ＊＊
    0.07
    Cab
    0.07
     obr
    0.07
     máxim
    0.07
     laga
    0.07
    207
    0.07
    Activations Density 0.001%

    No Known Activations