© 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. 21304
    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
    яване
    -0.08
     šo
    -0.08
     pẹlu
    -0.08
     dengan
    -0.08
    .Dispose
    -0.08
    Joining
    -0.07
     peluang
    -0.07
     visok
    -0.07
     naszym
    -0.07
     vysok
    -0.07
    POSITIVE LOGITS
     typical
    0.12
     eines
    0.11
     будто
    0.11
     seorang
    0.11
     unui
    0.11
     someone
    0.10
     characteristic
    0.10
     típico
    0.10
     обычно
    0.10
     unei
    0.10
    Activations Density 0.017%

    No Known Activations