© 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. 22732
    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
     اختلاف
    -0.08
     inclusão
    -0.08
    َم
    -0.08
    Opportunity
    -0.08
     slecht
    -0.08
     ಚಿಕಿತ್ಸ
    -0.08
     تغيير
    -0.08
    اردة
    -0.07
     ulike
    -0.07
     vermelho
    -0.07
    POSITIVE LOGITS
     reconstructed
    0.17
     meaningful
    0.16
     reconstruct
    0.15
     reconstruction
    0.15
     original
    0.15
     plaintext
    0.15
     Reconstruction
    0.14
    decoded
    0.14
     rekon
    0.14
     restored
    0.14
    Activations Density 0.017%

    No Known Activations