© 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. 19319
    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
     resid
    -0.08
     nepos
    -0.07
    inki
    -0.07
    ±
    -0.07
    ciu
    -0.07
    pose
    -0.07
     dört
    -0.07
    ciem
    -0.07
    full
    -0.07
     insured
    -0.07
    POSITIVE LOGITS
    átil
    0.09
     تستطيع
    0.09
    альность
    0.09
     eaux
    0.08
     ง
    0.08
    aterials
    0.08
    ادرة
    0.08
     ماء
    0.08
     specializes
    0.08
     released
    0.08
    Activations Density 0.000%

    No Known Activations