© 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. 44671
    Prev
    Next
    INDEX
    Explanations

    correction

    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
     поле
    -0.09
     farm
    -0.09
     Hosted
    -0.08
    ए
    -0.08
     ranar
    -0.08
     云
    -0.08
     Litt
    -0.08
     Farm
    -0.08
     Fish
    -0.08
    лара
    -0.08
    POSITIVE LOGITS
     cascading
    0.08
    0.08
    ouncing
    0.08
    MM
    0.07
     đều
    0.07
    іль
    0.07
    bour
    0.07
    kul
    0.07
    568
    0.07
    Merk
    0.07
    Activations Density 0.000%
    No Known Activations