© 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. 21870
    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
     but
    -0.13
     nhưng
    -0.12
    but
    -0.12
     pero
    -0.11
     ولكن
    -0.11
     tetapi
    -0.11
     но
    -0.10
     ngunit
    -0.10
    但
    -0.10
     mutta
    -0.10
    POSITIVE LOGITS
     díky
    0.11
     whenever
    0.11
     있도록
    0.10
     somehow
    0.10
     luckily
    0.10
    Luckily
    0.10
     dankzij
    0.10
    도록
    0.10
     magically
    0.10
     graças
    0.09
    Activations Density 0.066%

    No Known Activations