© 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. 19-RESID-POST-AA
    11. 18327
    Prev
    Next
    INDEX
    Explanations

    say "the ending .telegram or .windows"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     submarine
    -0.08
    াদক
    -0.08
    هذا
    -0.08
    soir
    -0.08
     weich
    -0.08
    -core
    -0.07
     directeur
    -0.07
     देते
    -0.07
     peito
    -0.07
     הגדול
    -0.07
    POSITIVE LOGITS
     toolkit
    0.08
    localhost
    0.08
     Logic
    0.08
     When
    0.08
     keys
    0.07
    quisites
    0.07
    .Func
    0.07
     Reihe
    0.07
     Elements
    0.07
     logic
    0.07
    Activations Density 0.006%

    No Known Activations