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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6333
    Prev
    Next
    INDEX
    Explanations

    Training intensity

    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
     Accord
    -0.09
     scu
    -0.08
     wicker
    -0.08
     escuelas
    -0.08
    胖
    -0.08
    orage
    -0.07
     Glasgow
    -0.07
    aline
    -0.07
     školy
    -0.07
     Sporting
    -0.07
    POSITIVE LOGITS
     intensidade
    0.10
     трен
    0.10
     trainingen
    0.10
     intenso
    0.10
     intensity
    0.10
     trening
    0.09
    0.09
    Intensity
    0.09
     intensa
    0.09
     intensidad
    0.09
    Activations Density 0.070%
    No Known Activations