© 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. 51144
    Prev
    Next
    INDEX
    Explanations

    sit

    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
     jugu
    -0.09
     hankali
    -0.08
     γίνεται
    -0.08
    _language
    -0.08
    ٥
    -0.08
     =↵
    -0.08
     banjur
    -0.08
    Garden
    -0.08
    ５
    -0.08
    Such
    -0.07
    POSITIVE LOGITS
    ters
    0.12
    -down
    0.10
    terness
    0.10
    utation
    0.10
     down
    0.09
    ational
    0.09
    utations
    0.09
    downs
    0.09
    DOWN
    0.09
    tting
    0.09
    Activations Density 0.014%

    No Known Activations