© 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. 70559
    Prev
    Next
    INDEX
    Explanations

    Buffet

    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
    urnal
    -0.07
    TZID
    -0.07
    olak
    -0.07
     remainder
    -0.07
    Msgs
    -0.07
    utzt
    -0.07
    شنا
    -0.07
    天下
    -0.07
     سجل
    -0.07
     ದಾಖಲ
    -0.07
    POSITIVE LOGITS
     buffet
    0.13
     miễn
    0.10
     cater
    0.09
    buff
    0.09
     bowl
    0.09
     catering
    0.09
     Buffet
    0.08
     platter
    0.08
     বু�
    0.08
    .enum
    0.08
    Activations Density 0.038%

    No Known Activations