© 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. 20841
    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
    their
    -0.10
     זו
    -0.10
    ישהו
    -0.09
    Their
    -0.09
    ₹
    -0.09
     ένας
    -0.09
    uang
    -0.09
    हे
    -0.08
    यह
    -0.08
    ণ্য
    -0.08
    POSITIVE LOGITS
     المختلفة
    0.20
     الخاصة
    0.19
     الصحي
    0.19
     الأكثر
    0.18
     اللازمة
    0.18
     الأساسية
    0.18
     الأكبر
    0.17
     التي
    0.17
     الفنية
    0.17
     المتعلقة
    0.17
    Activations Density 0.036%

    No Known Activations