© 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. 110420
    Prev
    Next
    INDEX
    Explanations

    "_data"

    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
    chelle
    -0.08
     לת
    -0.08
     القض
    -0.08
    書
    -0.07
     ross
    -0.07
    ?↵
    -0.07
     neh
    -0.07
     Ross
    -0.07
    ácie
    -0.07
     PSP
    -0.07
    POSITIVE LOGITS
     Tire
    0.08
     tire
    0.08
    િં
    0.08
     Step
    0.08
     daban
    0.07
     poisonous
    0.07
    Step
    0.07
     Доп
    0.07
     lado
    0.07
     milliard
    0.07
    Activations Density 0.001%

    No Known Activations