© 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. 21505
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    obald
    -0.10
    unku
    -0.09
    erk
    -0.09
    vergleich
    -0.09
    hook
    -0.09
    eing
    -0.08
    lx
    -0.08
    ometers
    -0.08
     yhdessä
    -0.08
    ystore
    -0.08
    POSITIVE LOGITS
     паміж
    0.13
     giữa
    0.12
     между
    0.12
     між
    0.12
     between
    0.12
     בין
    0.12
     mellom
    0.11
     między
    0.11
     generaciones
    0.11
     mellem
    0.11
    Activations Density 0.003%

    No Known Activations