© 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. 19466
    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
    拥有
    -0.08
     headquartered
    -0.08
     someday
    -0.08
     unlaw
    -0.08
     தனது
    -0.08
    领先
    -0.08
     øst
    -0.08
     гориз
    -0.08
    大陆
    -0.08
     തന്റെ
    -0.08
    POSITIVE LOGITS
     विद्यार्थ
    0.18
     વિદ્યાર્થીઓ
    0.17
     छात्रों
    0.17
     students
    0.17
    教师
    0.16
     ವಿದ್ಯಾರ್ಥ
    0.16
    students
    0.16
     শিক্ষক
    0.16
     Encourage
    0.16
    Students
    0.16
    Activations Density 0.074%

    No Known Activations