© 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. 11-RESID-POST-AA
    11. 24833
    Prev
    Next
    INDEX
    Explanations

    desserts soaked in syrup

    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
    अ
    -0.08
    ستخدام
    -0.08
     अंतिम
    -0.07
    'informations
    -0.07
    urf
    -0.07
     Smith
    -0.07
     cultivar
    -0.07
     Saf
    -0.07
    Sarah
    -0.07
     typing
    -0.07
    POSITIVE LOGITS
    Anal
    0.08
     esteve
    0.08
     suspensión
    0.08
     сеть
    0.08
    Parametro
    0.08
    െടുത്തു
    0.07
    Den
    0.07
     geschaffen
    0.07
     الثقيلة
    0.07
    ిల్ల
    0.07
    Activations Density 0.008%

    No Known Activations