© 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. 19-RESID-POST-AA
    11. 102908
    Prev
    Next
    INDEX
    Explanations

    distractions

    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
     заключ
    -0.08
     пропис
    -0.08
     tarieven
    -0.08
     лит
    -0.07
    申
    -0.07
    必赢
    -0.07
     chambers
    -0.07
    uniq
    -0.07
     pamoja
    -0.07
     signed
    -0.07
    POSITIVE LOGITS
     distractions
    0.45
     distraction
    0.41
     distracting
    0.41
     distract
    0.40
     distracted
    0.37
     distra
    0.37
     Distr
    0.29
     отв
    0.29
    Distr
    0.28
     diversion
    0.24
    Activations Density 0.056%

    No Known Activations