© 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. 22243
    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
    ваю
    -0.09
    yeed
    -0.09
    amentul
    -0.08
    ichtet
    -0.08
    верж
    -0.08
    дыр
    -0.08
     kés
    -0.08
    weke
    -0.08
    ged
    -0.08
    вает
    -0.07
    POSITIVE LOGITS
    .white
    0.12
    -white
    0.12
    Smoke
    0.11
    洁
    0.11
     સફ
    0.11
    _white
    0.11
    白
    0.10
     putih
    0.10
    white
    0.10
     blanca
    0.10
    Activations Density 0.007%

    No Known Activations