© 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. 19419
    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
     ремонта
    -0.09
     മാത്രം
    -0.08
     ενός
    -0.08
     motherhood
    -0.08
     mother's
    -0.08
     исполнения
    -0.08
     pelanggan
    -0.08
     produktu
    -0.08
     شيء
    -0.08
     продукта
    -0.08
    POSITIVE LOGITS
    ologists
    0.24
    ists
    0.24
    ians
    0.23
     scientists
    0.20
    ian
    0.19
    ologist
    0.19
    ist
    0.19
     physic
    0.17
     historians
    0.17
     researchers
    0.16
    Activations Density 0.018%

    No Known Activations