© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 102267
    Prev
    Next
    INDEX
    Explanations

    minutes

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Let's
    -0.08
     is
    -0.08
     আমরা
    -0.08
    multiple
    -0.07
     Multiple
    -0.07
     We
    -0.07
     can
    -0.07
    ，我们
    -0.07
     Every
    -0.07
     For
    -0.07
    POSITIVE LOGITS
     минуты
    0.17
     minutes
    0.17
     دقائق
    0.16
     минут
    0.16
     דקות
    0.16
     seconds
    0.15
     phút
    0.15
     дней
    0.15
     minutter
    0.15
     секунд
    0.15
    Activations Density 0.011%

    No Known Activations