© 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. 19209
    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
    。截至
    -0.09
     pursuant
    -0.09
     प्रदान
    -0.08
     undertake
    -0.08
    ]').
    -0.08
    กรรม
    -0.08
     sprake
    -0.08
     assessed
    -0.08
    isiwe
    -0.08
     substantive
    -0.08
    POSITIVE LOGITS
     remembering
    0.22
     memorize
    0.22
     기억
    0.20
    牢记
    0.19
    口诀
    0.19
     remember
    0.19
     Remember
    0.18
     mastering
    0.18
     memor
    0.17
    Remember
    0.17
    Activations Density 0.032%

    No Known Activations