© 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. 44432
    Prev
    Next
    INDEX
    Explanations

    charge

    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
     waved
    -0.08
     plastik
    -0.08
    ophen
    -0.08
     Ress
    -0.08
     daim
    -0.08
     yangi
    -0.08
     hidrául
    -0.08
     rodas
    -0.08
    slick
    -0.07
    arker
    -0.07
    POSITIVE LOGITS
     decay
    0.07
    ½
    0.07
    ஆ
    0.07
     recherches
    0.07
     bulk
    0.07
    直到
    0.07
     vigilant
    0.07
     فقد
    0.07
    .rf
    0.07
     decent
    0.07
    Activations Density 0.001%

    No Known Activations