© 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. 19-RESID-POST-AA
    11. 102742
    Prev
    Next
    INDEX
    Explanations

    wrought

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     byi
    -0.11
     by
    -0.09
     via
    -0.09
    via
    -0.09
    ially
    -0.09
     byw
    -0.09
    lessly
    -0.08
     Nhưng
    -0.08
    mux
    -0.08
     Simulation
    -0.08
    POSITIVE LOGITS
     sugar
    0.13
     wheat
    0.12
     milk
    0.12
     vegetable
    0.12
     glass
    0.12
     soybean
    0.12
     cheese
    0.12
     oil
    0.11
     iron
    0.11
     horse
    0.11
    Activations Density 0.024%

    No Known Activations