© 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. 21943
    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
     if
    -0.09
     (*)
    -0.08
     बू
    -0.08
    ucid
    -0.08
     unaware
    -0.08
    이고
    -0.08
     delic
    -0.08
     menace
    -0.08
     and
    -0.08
     he'd
    -0.08
    POSITIVE LOGITS
     warranty
    0.11
     airbags
    0.10
     compass
    0.09
     Warranty
    0.09
     второго
    0.09
     δεύτε
    0.09
     GPS
    0.09
     warranties
    0.08
     maraming
    0.08
     दूसरा
    0.08
    Activations Density 0.004%

    No Known Activations