© 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. 103429
    Prev
    Next
    INDEX
    Explanations

    doing things effectively

    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
     qualche
    -0.10
     einige
    -0.10
    कुछ
    -0.09
     некоторое
    -0.09
     doono
    -0.09
     kèk
    -0.08
     केही
    -0.08
     ڪجهه
    -0.08
     możliwość
    -0.08
     einigen
    -0.08
    POSITIVE LOGITS
     efficacement
    0.22
     эффективно
    0.18
     effectively
    0.16
     oneself
    0.16
     effectief
    0.16
     efficiently
    0.15
     eficaz
    0.15
     effektiv
    0.15
     правильно
    0.14
     correctamente
    0.14
    Activations Density 0.215%

    No Known Activations