© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48061
    Prev
    Next
    INDEX
    Explanations

    F

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Joachim
    -0.08
    kje
    -0.08
     Johansson
    -0.08
    daj
    -0.08
    ాంటి
    -0.08
     Herzog
    -0.07
    prototype
    -0.07
    tributing
    -0.07
    unka
    -0.07
    seits
    -0.07
    POSITIVE LOGITS
    り
    0.08
    anes
    0.07
    ane
    0.07
     odi
    0.07
     comentar
    0.07
    เติม
    0.07
    ят
    0.07
    Drive
    0.07
    ви
    0.07
    ovec
    0.07
    Activations Density 0.000%

    No Known Activations