© 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. 21891
    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
     specifically
    -0.09
     especificamente
    -0.09
     específicamente
    -0.09
     partially
    -0.08
     häufiger
    -0.08
     parcialmente
    -0.08
     чаще
    -0.08
    .partial
    -0.08
     slightly
    -0.07
     гораздо
    -0.07
    POSITIVE LOGITS
     після
    0.10
    Após
    0.10
     после
    0.09
     after
    0.09
     После
    0.09
     setelah
    0.09
    after
    0.09
    Après
    0.09
    ท้าย
    0.09
     após
    0.09
    Activations Density 0.004%

    No Known Activations