© 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. 49862
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
     jez
    -0.08
     kompat
    -0.08
     compatibility
    -0.08
     Mee
    -0.08
    Compatibility
    -0.08
     Compatibility
    -0.08
    .compat
    -0.07
    ন্দর
    -0.07
    doo
    -0.07
    nam
    -0.07
    POSITIVE LOGITS
    0.09
    ACION
    0.08
    olean
    0.08
    _BIG
    0.08
    ación
    0.08
    ೇ
    0.07
    ainted
    0.07
    elligence
    0.07
    ಲೀ
    0.07
    épend
    0.07
    Activations Density 0.000%
    No Known Activations