© 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. 22403
    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
    systems
    -0.08
    sidebar
    -0.08
     Plaint
    -0.07
     מער
    -0.07
     לכן
    -0.07
     מול
    -0.07
     উপর
    -0.07
     mezi
    -0.07
    Taxes
    -0.07
     Guerr
    -0.07
    POSITIVE LOGITS
     learning
    0.15
     öğren
    0.14
    learning
    0.13
    学习
    0.13
    _learning
    0.13
    -learning
    0.12
     Learning
    0.12
     aprendizaje
    0.12
    .learning
    0.12
     सीख
    0.12
    Activations Density 0.008%

    No Known Activations