© 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. 63834
    Prev
    Next
    INDEX
    Explanations

    clouds

    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
    analytics
    -0.09
     combien
    -0.08
    td
    -0.08
    PORT
    -0.07
     version
    -0.07
     debt
    -0.07
     Debt
    -0.07
    Statistic
    -0.07
    นี้
    -0.07
     Documento
    -0.07
    POSITIVE LOGITS
     ador
    0.08
     чов
    0.08
     greg
    0.08
     atop
    0.08
     sunny
    0.08
     jut
    0.08
     ley
    0.08
     pope
    0.08
     круп
    0.08
    odies
    0.08
    Activations Density 0.005%

    No Known Activations