© 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. 11-RESID-POST-AA
    11. 65399
    Prev
    Next
    INDEX
    Explanations

    Code imports

    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
     отс
    -0.09
     мың
    -0.08
     ultra
    -0.08
    haust
    -0.08
     кез
    -0.08
     чрез
    -0.08
     қалған
    -0.07
    头像
    -0.07
    .seq
    -0.07
    uristic
    -0.07
    POSITIVE LOGITS
     Counties
    0.08
     SI
    0.07
    Bund
    0.07
    ेय
    0.07
     Moose
    0.07
     Gan
    0.07
     Pemer
    0.07
     modi
    0.07
     CIA
    0.07
    thing
    0.07
    Activations Density 0.001%

    No Known Activations