© 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. 21631
    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
     you're
    -0.09
     eius
    -0.08
    ř
    -0.08
    -that
    -0.08
     such
    -0.08
     that
    -0.08
    asers
    -0.08
     isn't
    -0.08
     pot
    -0.08
     individual's
    -0.07
    POSITIVE LOGITS
     العمل
    0.09
    analysis
    0.09
    <|end|>
    0.09
    markdown
    0.09
     Markdown
    0.08
    Detailed
    0.08
     эксперт
    0.08
     brainstorming
    0.08
     переговор
    0.08
     السؤال
    0.08
    Activations Density 0.043%

    No Known Activations