© 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. 30458
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     tro
    -0.07
     umuntu
    -0.07
     bong
    -0.07
     台
    -0.07
     modul
    -0.07
     Edith
    -0.07
    吨
    -0.07
    Баш
    -0.07
     巴
    -0.07
    “As
    -0.07
    POSITIVE LOGITS
    decltype
    0.09
    ostream
    0.07
     obtenido
    0.07
     celebrities
    0.07
     contient
    0.07
    ിനിമ
    0.07
    =is
    0.07
    ைப்
    0.07
    ほ
    0.07
     veroorzaken
    0.07
    Activations Density 0.000%

    No Known Activations