© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 63209
    Prev
    Next
    INDEX
    Explanations

    content

    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
     tempest
    -0.07
    Do
    -0.07
    kur
    -0.07
    cent
    -0.07
    arque
    -0.07
    人生
    -0.07
     stewardship
    -0.07
    -0.07
    do
    -0.07
     Tala
    -0.07
    POSITIVE LOGITS
    撑
    0.08
    0.08
    	errors
    0.08
     ให
    0.08
    லும்
    0.08
     beperk
    0.08
     rộng
    0.07
     sandwiches
    0.07
    алки
    0.07
     sugars
    0.07
    Activations Density 0.003%
    No Known Activations