© 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. 11-RESID-POST-AA
    11. 47136
    Prev
    Next
    INDEX
    Explanations

    xmlns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oration
    -0.08
     variations
    -0.07
     game
    -0.07
    Variation
    -0.07
    loat
    -0.07
    lut
    -0.07
    solve
    -0.07
    rock
    -0.07
    phe
    -0.07
    -0.07
    POSITIVE LOGITS
     бухгалтер
    0.09
     Vás
    0.08
     wor
    0.08
     yorum
    0.08
    �
    0.08
    .forms
    0.08
     ಕಾಮ
    0.08
     �
    0.08
     зв
    0.08
     Qt
    0.08
    Activations Density 0.000%
    No Known Activations