© 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. 18566
    Prev
    Next
    INDEX
    Explanations

    code, equations

    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
     случ
    -0.08
     وتس
    -0.08
     עכשיו
    -0.08
     nüüd
    -0.07
     digitais
    -0.07
    šlo
    -0.07
     suʻ
    -0.07
    ({↵↵
    -0.07
     freel
    -0.07
    inten
    -0.07
    POSITIVE LOGITS
     تلك
    0.08
     That
    0.08
    .gridy
    0.08
    _round
    0.08
    ucks
    0.08
     त्या
    0.08
    .character
    0.07
    러한
    0.07
    .correct
    0.07
    .round
    0.07
    Activations Density 0.000%

    No Known Activations