© 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. 99373
    Prev
    Next
    INDEX
    Explanations

    Math indices and sequences

    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
    _PRIMARY
    -0.08
     QByte
    -0.07
    Producto
    -0.07
     primaria
    -0.07
    aww
    -0.07
    Loader
    -0.07
    rea
    -0.07
    Transform
    -0.07
    Pes
    -0.07
    Neue
    -0.07
    POSITIVE LOGITS
     decreasing
    0.13
     decrease
    0.12
    descending
    0.12
     downward
    0.12
     descending
    0.12
    Descending
    0.12
     reversed
    0.12
     decreased
    0.11
    下降
    0.11
    (reverse
    0.11
    Activations Density 0.059%

    No Known Activations