© 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. 78381
    Prev
    Next
    INDEX
    Explanations

    coil

    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
    禽
    -0.08
     peng
    -0.08
     lingering
    -0.08
     아니
    -0.07
     papill
    -0.07
     aith
    -0.07
     amy
    -0.07
    aland
    -0.07
     maupun
    -0.07
    ints
    -0.07
    POSITIVE LOGITS
    viz
    0.07
     SDA
    0.07
    .gen
    0.07
    dy
    0.07
     Rund
    0.07
    bomb
    0.07
    Bomb
    0.07
     Г
    0.07
     Springs
    0.07
     springs
    0.07
    Activations Density 0.002%

    No Known Activations