© 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. 19220
    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
     They
    -0.09
     եթե
    -0.09
     hvis
    -0.09
     dacă
    -0.08
    They
    -0.08
    ótico
    -0.08
     पूछा
    -0.08
     dersom
    -0.08
    Iedere
    -0.08
     यदि
    -0.08
    POSITIVE LOGITS
     подробнее
    0.11
     التفاصيل
    0.11
     specifics
    0.11
     guidance
    0.10
     possibilities
    0.10
     your
    0.10
    よろしく
    0.10
     freue
    0.10
     방향
    0.10
    .details
    0.10
    Activations Density 0.010%

    No Known Activations