© 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. 19818
    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
     díky
    -0.10
     BOTH
    -0.09
     (~
    -0.08
    _even
    -0.08
     навіть
    -0.08
     싶
    -0.08
     nawet
    -0.08
     Даже
    -0.08
     Dzięki
    -0.08
    -го
    -0.08
    POSITIVE LOGITS
     museums
    0.11
     обеспечение
    0.10
     prévention
    0.10
     организации
    0.10
     обеспечения
    0.10
     fortalec
    0.10
     مكافحة
    0.10
     prevention
    0.10
     meningkatkan
    0.10
     prevención
    0.09
    Activations Density 0.010%

    No Known Activations