© 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. 21557
    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
    ствуют
    -0.10
    ствовать
    -0.09
    λογία
    -0.09
     کہتے
    -0.09
    -0.09
     define
    -0.09
    izantes
    -0.09
    �니다
    -0.09
    -0.09
     hãy
    -0.09
    POSITIVE LOGITS
    された
    0.32
    된
    0.31
     edilmiş
    0.23
     شده
    0.23
     செய்யப்பட்ட
    0.23
     થય
    0.22
     된
    0.21
     edilen
    0.20
    済
    0.20
    되는
    0.19
    Activations Density 0.022%

    No Known Activations