© 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. 64518
    Prev
    Next
    INDEX
    Explanations

    of

    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
    -vers
    -0.07
    (+
    -0.07
    、中国
    -0.07
    .pause
    -0.07
     eriti
    -0.07
    _PA
    -0.07
     chuyển
    -0.07
    /J
    -0.07
     unwind
    -0.07
     eten
    -0.07
    POSITIVE LOGITS
     ذهن
    0.09
     головы
    0.08
     bedacht
    0.08
    紙
    0.08
    ৎ
    0.08
    仁
    0.07
     fridge
    0.07
     مین
    0.07
     wahr
    0.07
    乎
    0.07
    Activations Density 0.012%

    No Known Activations