© 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. 22131
    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
     प्रत्येक
    -0.10
    Each
    -0.10
    ，每
    -0.09
     દરેક
    -0.09
    gebruik
    -0.09
     Each
    -0.09
    _each
    -0.09
    each
    -0.09
    每
    -0.09
     Iedere
    -0.08
    POSITIVE LOGITS
     polygon
    0.13
     trape
    0.12
    Polygon
    0.11
     three
    0.11
     трех
    0.11
     három
    0.11
     drie
    0.11
     üç
    0.11
     ಮೂರು
    0.11
     três
    0.11
    Activations Density 0.007%

    No Known Activations