© 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. 21998
    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
     Pourquoi
    -0.10
    ),
    -0.10
     pourquoi
    -0.10
    »,
    -0.10
     почему
    -0.10
     hvorfor
    -0.10
    Pourquoi
    -0.10
     warum
    -0.10
     »,
    -0.09
     उन्होंने
    -0.09
    POSITIVE LOGITS
     ensure
    0.13
     सुनिश्चित
    0.12
    Ensure
    0.12
     zapew
    0.12
     ensuring
    0.11
     নিশ্চিত
    0.11
     gewährleisten
    0.10
     Ensure
    0.10
     обеспечить
    0.10
     asegura
    0.10
    Activations Density 0.011%

    No Known Activations