© 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. 65540
    Prev
    Next
    INDEX
    Explanations

    then therefore

    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
    Nest
    -0.08
     nest
    -0.08
     Nest
    -0.08
     어
    -0.08
    据
    -0.07
     delimiter
    -0.07
     '='
    -0.07
    李
    -0.07
     ню
    -0.07
    언
    -0.07
    POSITIVE LOGITS
    wards
    0.08
    forth
    0.08
     Ruf
    0.07
     inneh
    0.07
    że
    0.07
     embody
    0.07
     الحم
    0.07
    mehr
    0.07
     urgent
    0.07
    ¼
    0.07
    Activations Density 0.041%

    No Known Activations