© 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. 63964
    Prev
    Next
    INDEX
    Explanations

    CSS media queries

    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
    牢
    -0.09
    创造
    -0.08
    踏
    -0.08
     toilette
    -0.08
     África
    -0.08
     душ
    -0.08
    זרה
    -0.08
    aleza
    -0.08
    yum
    -0.08
    tritur
    -0.07
    POSITIVE LOGITS
    Threshold
    0.09
     threshold
    0.09
    threshold
    0.08
     Sánchez
    0.08
     sidebar
    0.08
    XAxis
    0.08
    px
    0.08
     المحمولة
    0.07
     thresholds
    0.07
    reshold
    0.07
    Activations Density 0.001%

    No Known Activations