© 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. 79435
    Prev
    Next
    INDEX
    Explanations

    Evil

    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
     atheist
    -0.08
     elé
    -0.08
    .lo
    -0.07
     repar
    -0.07
    sth
    -0.07
     Calvin
    -0.07
     <$
    -0.07
     legislature
    -0.07
    orben
    -0.07
    allist
    -0.07
    POSITIVE LOGITS
    Parte
    0.08
    開
    0.08
    際
    0.08
     curator
    0.08
    Preview
    0.08
     Parte
    0.08
     الجزء
    0.07
     telef
    0.07
     المؤ
    0.07
    -form
    0.07
    Activations Density 0.002%

    No Known Activations