© 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. 19028
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     это
    -0.10
     Tämä
    -0.10
     This
    -0.10
    With
    -0.09
     manage
    -0.09
    This
    -0.09
     이것
    -0.09
     මෙ
    -0.09
     этого
    -0.09
     With
    -0.09
    POSITIVE LOGITS
    สอบ
    0.08
     conditions
    0.07
    \Bundle
    0.07
     ראש
    0.07
     ў
    0.07
     in
    0.07
     توقع
    0.07
     condiciones
    0.07
     संद
    0.07
    ước
    0.07
    Activations Density 0.500%

    No Known Activations