© 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. 19803
    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
    ,this
    -0.10
    ভাবে
    -0.09
     होकर
    -0.09
    `).
    -0.09
    ’Um
    -0.09
    ப்
    -0.09
     ہونے
    -0.09
     ამის
    -0.09
     Wannan
    -0.08
     হওয়ার
    -0.08
    POSITIVE LOGITS
    possibly
    0.11
     或
    0.11
     perhaps
    0.11
    maybe
    0.11
    perhaps
    0.11
     or
    0.11
     måske
    0.11
     misschien
    0.10
    或
    0.10
     possibly
    0.10
    Activations Density 0.075%

    No Known Activations