© 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. 22428
    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
     Pre
    -0.10
    Pre
    -0.08
    quê
    -0.08
    pre
    -0.08
     fores
    -0.08
    Upcoming
    -0.08
     Near
    -0.08
     Rol
    -0.08
     Pré
    -0.07
     Around
    -0.07
    POSITIVE LOGITS
     voordat
    0.25
     прежде
    0.24
     לפני
    0.22
     before
    0.22
     abans
    0.22
     innan
    0.21
     antes
    0.21
     áður
    0.21
     sebelum
    0.20
     قبل
    0.20
    Activations Density 0.023%

    No Known Activations