© 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 EvalsExportsAPI 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. 20418
    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
     uiteraard
    -0.12
     כמובן
    -0.11
     tentunya
    -0.10
     eveneens
    -0.09
     იგი
    -0.09
    ՛
    -0.09
     jederzeit
    -0.09
     بداية
    -0.09
     selvfølgelig
    -0.09
     selbstverständlich
    -0.09
    POSITIVE LOGITS
     waardoor
    0.14
     khiến
    0.13
     such
    0.12
     constraints
    0.12
     relating
    0.12
     interplay
    0.12
    导致
    0.12
     that
    0.12
     ensuring
    0.12
     involving
    0.12
    Activations Density 0.050%

    No Known Activations