© 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 EvalsExportsAPI 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. 20166
    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
     untuk
    -0.09
     เพื่อ
    -0.09
     to
    -0.09
     لتحقيق
    -0.09
    Untuk
    -0.09
     logrado
    -0.09
     Untuk
    -0.08
     जाकर
    -0.08
    ើម្បី
    -0.08
     To
    -0.08
    POSITIVE LOGITS
     necesitas
    0.18
     نیاز
    0.18
     нужно
    0.17
    需要
    0.17
     need
    0.17
     нужны
    0.16
     gerekir
    0.16
     bezwen
    0.15
     необходимо
    0.15
     საჭირ
    0.15
    Activations Density 0.052%

    No Known Activations