© 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. 71293
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Estr
    -0.08
    ething
    -0.08
    Mine
    -0.07
     sting
    -0.07
    Cos
    -0.07
     conducteur
    -0.07
     chất
    -0.07
     goodness
    -0.07
     dialogue
    -0.07
     exert
    -0.07
    POSITIVE LOGITS
     wees
    0.08
    halts
    0.08
    ({
    0.07
    ({'
    0.07
     von
    0.07
    (Intent
    0.07
     Schmidt
    0.07
    _kind
    0.07
     egestas
    0.07
    ultipart
    0.07
    Activations Density 0.033%

    No Known Activations