© 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 EvalsExportsinterp-engineNEWAPI 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. 110796
    Prev
    Next
    INDEX
    Explanations

    number 4

    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
     七
    -0.08
     Sans
    -0.08
    /rest
    -0.08
     Pū
    -0.07
     영어
    -0.07
     Vertrauen
    -0.07
     Younger
    -0.07
     |>
    -0.07
     pada
    -0.07
    走
    -0.07
    POSITIVE LOGITS
    -tier
    0.11
    teenth
    0.09
     ধরনের
    0.08
    ψη
    0.08
    emming
    0.08
    -dimensional
    0.08
    quel
    0.08
    টি
    0.08
    -legged
    0.08
     interconnected
    0.08
    Activations Density 0.090%

    No Known Activations