© 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. 23-RESID-POST-AA
    11. 50619
    Prev
    Next
    INDEX
    Explanations

    umlauts

    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
     afgelopen
    -0.09
    usive
    -0.09
     burnt
    -0.08
    legging
    -0.08
     ട്ര
    -0.08
    asan
    -0.08
     Webster
    -0.07
     טר
    -0.07
     ట్ర
    -0.07
     ટ્ર
    -0.07
    POSITIVE LOGITS
    öch
    0.09
    ੈਂ
    0.08
    ändige
    0.08
    licherweise
    0.08
    ünde
    0.08
    teva
    0.08
    øse
    0.08
    him
    0.07
    ö
    0.07
    ßte
    0.07
    Activations Density 0.001%

    No Known Activations