© 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. 22043
    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
    iminal
    -0.09
     salle
    -0.09
     muur
    -0.08
     помещении
    -0.08
    tablename
    -0.08
     помещение
    -0.08
    umbotron
    -0.08
    ентар
    -0.08
     wall
    -0.08
    ễ
    -0.08
    POSITIVE LOGITS
     livros
    0.13
     textbooks
    0.13
     الكتب
    0.12
     novels
    0.12
     unopened
    0.12
     unfinished
    0.12
     discarded
    0.12
     unused
    0.11
     પુસ્ત
    0.11
     papers
    0.11
    Activations Density 0.021%

    No Known Activations