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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 112609
    Prev
    Next
    INDEX
    Explanations

    languages

    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
    ్ట
    -0.08
    �
    -0.08
     rebels
    -0.08
    oddi
    -0.08
     rebellion
    -0.08
     taxis
    -0.08
    очка
    -0.08
     pumps
    -0.07
    тация
    -0.07
    恋
    -0.07
    POSITIVE LOGITS
     nutritional
    0.08
    uteur
    0.08
     topical
    0.07
    arı
    0.07
    lü
    0.07
     돌아
    0.07
    actal
    0.07
     bewaren
    0.07
    Nutrition
    0.07
     nutrition
    0.07
    Activations Density 0.001%

    No Known Activations