© 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. 19463
    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
     تولید
    -0.09
    ождения
    -0.08
     उत्पादन
    -0.08
     üret
    -0.08
     निर्माण
    -0.08
    ��������
    -0.08
     अन्य
    -0.08
     विशाल
    -0.08
     निर्माता
    -0.08
     सड़क
    -0.08
    POSITIVE LOGITS
     escola
    0.09
     homeschooling
    0.08
    illis
    0.08
     torcida
    0.08
     cris
    0.08
    cris
    0.08
     homeschool
    0.08
     flore
    0.08
     gols
    0.08
    .enc
    0.08
    Activations Density 0.001%

    No Known Activations