© 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. 63267
    Prev
    Next
    INDEX
    Explanations

    g

    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
     Harding
    -0.08
     Ske
    -0.07
     nay
    -0.07
     arrog
    -0.07
    vid
    -0.07
     Umwelt
    -0.07
    tp
    -0.07
     credited
    -0.07
     Scal
    -0.07
     Zav
    -0.07
    POSITIVE LOGITS
     MQTT
    0.09
     titulo
    0.08
    JUnit
    0.08
    щу
    0.08
    ונג
    0.08
     المرج
    0.08
     burial
    0.08
    킨
    0.08
     المطر
    0.08
     ипот
    0.08
    Activations Density 0.001%

    No Known Activations