© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7777
    Prev
    Next
    INDEX
    Explanations

    Name or title

    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
    Witness
    -0.09
    atae
    -0.09
     Manc
    -0.08
    \Exceptions
    -0.08
    Determ
    -0.08
     મુશ્ક
    -0.08
    Forget
    -0.07
    ugn
    -0.07
    LOY
    -0.07
    ố
    -0.07
    POSITIVE LOGITS
    链接
    0.10
     щоб
    0.09
    リンク
    0.09
     чтобы
    0.09
     December
    0.08
     Little
    0.08
     כדי
    0.08
     enlaces
    0.08
     لینک
    0.08
     成
    0.08
    Activations Density 0.017%

    No Known Activations