© 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. 43580
    Prev
    Next
    INDEX
    Explanations

    produce/provide

    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
     lama
    -0.08
    spunkt
    -0.07
    产生
    -0.07
    adag
    -0.07
    人的
    -0.07
     allegedly
    -0.07
    -0.07
    conn
    -0.07
    Кат
    -0.07
    tys
    -0.07
    POSITIVE LOGITS
     assimilation
    0.09
     numbered
    0.08
     caution
    0.08
     Ru
    0.07
     sogen
    0.07
    icha
    0.07
     uburyo
    0.07
     başlang
    0.07
     şöyle
    0.07
     Knight
    0.07
    Activations Density 0.060%
    No Known Activations