© 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. 11-RESID-POST-AA
    11. 30250
    Prev
    Next
    INDEX
    Explanations

    particle physics

    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
    Grp
    -0.08
    Layer
    -0.08
     grp
    -0.08
     Layer
    -0.07
     сезон
    -0.07
    латы
    -0.07
     популярных
    -0.07
    <Group
    -0.07
    -0.07
     grains
    -0.07
    POSITIVE LOGITS
     overturn
    0.08
     compassion
    0.08
    Ｏ
    0.08
     DREAM
    0.08
     brak
    0.08
     wund
    0.08
     الحال
    0.08
     broadband
    0.08
     hina
    0.08
    /signup
    0.08
    Activations Density 0.001%
    No Known Activations