© 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. 23-RESID-POST-AA
    11. 49538
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     topl
    -0.08
     सभी
    -0.08
     Full
    -0.07
     AC
    -0.07
     तीस
    -0.07
     softer
    -0.07
     Bluetooth
    -0.07
    ized
    -0.07
     trafficking
    -0.07
     MD
    -0.07
    POSITIVE LOGITS
     liegt
    0.09
     liegen
    0.08
     precaut
    0.08
    戰
    0.08
    John
    0.08
    Wake
    0.08
    оль
    0.08
    awake
    0.08
    .Allow
    0.08
    나는
    0.08
    Activations Density 0.001%

    No Known Activations