© 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. 21795
    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
     käyttää
    -0.10
     használ
    -0.10
     menggunakan
    -0.10
    使用
    -0.09
    Gebruik
    -0.09
     использовать
    -0.09
     verwenden
    -0.09
     использования
    -0.09
    Все
    -0.09
     gebruiken
    -0.09
    POSITIVE LOGITS
     сторону
    0.11
     some
    0.11
     direção
    0.11
     המקום
    0.10
     direction
    0.10
     אותה
    0.10
     стороне
    0.10
     the
    0.10
     which
    0.10
     portions
    0.10
    Activations Density 0.015%

    No Known Activations