© 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. 23-RESID-POST-AA
    11. 50949
    Prev
    Next
    INDEX
    Explanations

    December

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Feb
    -0.11
     février
    -0.11
     Februar
    -0.10
     February
    -0.10
     Februari
    -0.09
    Feb
    -0.09
     novembro
    -0.09
    February
    -0.09
     fevereiro
    -0.09
     febrero
    -0.09
    POSITIVE LOGITS
     ธันวาคม
    0.13
     December
    0.13
     dezembro
    0.13
     декабря
    0.13
     ഡിസ
    0.13
     ديسمبر
    0.12
     Dezember
    0.12
     diciembre
    0.12
     ડિસ
    0.11
     décembre
    0.11
    Activations Density 0.003%

    No Known Activations