© 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. 114086
    Prev
    Next
    INDEX
    Explanations

    multiplication

    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
    满
    -0.07
     prel
    -0.07
     logiciels
    -0.07
     веч
    -0.07
    будь
    -0.07
    ’utilisation
    -0.07
     doorstep
    -0.07
     semper
    -0.07
     прояв
    -0.07
     использование
    -0.07
    POSITIVE LOGITS
    901
    0.08
     público
    0.08
     Público
    0.07
     বর্ত
    0.07
     Hertz
    0.07
     Public
    0.07
     Sik
    0.07
     ck
    0.07
    cee
    0.07
     Slot
    0.07
    Activations Density 0.003%

    No Known Activations