© 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. 19983
    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
     correctement
    -0.10
     ճիշտ
    -0.09
     correta
    -0.09
    ებელია
    -0.09
     ọma
    -0.09
     дұрыс
    -0.09
    waard
    -0.09
    ക്കാട്
    -0.09
    യിലാണ്
    -0.09
     γνω
    -0.09
    POSITIVE LOGITS
     an
    0.10
     maximum
    0.10
     a
    0.10
     ultimate
    0.09
     maximale
    0.09
     added
    0.09
    maximum
    0.09
     maximal
    0.09
     heightened
    0.09
     zusätzlichen
    0.09
    Activations Density 0.013%

    No Known Activations