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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102159
    Prev
    Next
    INDEX
    Explanations

    parameters

    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
     steam
    -0.08
     meals
    -0.08
     Meals
    -0.08
     maalt
    -0.08
    Meals
    -0.08
     presentations
    -0.08
     আদাল
    -0.08
    影音
    -0.08
     Crime
    -0.07
     sporten
    -0.07
    POSITIVE LOGITS
     coefficients
    0.25
     parameters
    0.25
    _parameters
    0.23
    .parameters
    0.22
    parameters
    0.22
     Parameters
    0.21
     parâmetros
    0.21
    _params
    0.21
     parámetros
    0.21
    参数
    0.21
    Activations Density 0.017%

    No Known Activations