© 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. 21098
    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
    andaş
    -0.09
    	scroll
    -0.08
    ceased
    -0.08
     wohnhaft
    -0.08
     المكت
    -0.08
     sonore
    -0.08
    empuan
    -0.07
    .done
    -0.07
     المعت
    -0.07
    Scrollbar
    -0.07
    POSITIVE LOGITS
     competitions
    0.23
    比赛
    0.23
     соревн
    0.22
     tournament
    0.20
     competición
    0.20
     مسابق
    0.19
     compétition
    0.19
     competition
    0.19
     tournaments
    0.18
    考试
    0.18
    Activations Density 0.064%

    No Known Activations