© 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. 99863
    Prev
    Next
    INDEX
    Explanations

    system

    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
    という
    -0.08
     많은
    -0.08
     thesis
    -0.08
    ම
    -0.08
    Epic
    -0.08
    ůst
    -0.07
    bara
    -0.07
    gate
    -0.07
     दर
    -0.07
    라는
    -0.07
    POSITIVE LOGITS
    กำ
    0.08
     Richtung
    0.08
     Треб
    0.08
     وهم
    0.08
     Pert
    0.08
     perpendicular
    0.08
     Bridget
    0.08
    cen
    0.08
     iss
    0.08
    лся
    0.08
    Activations Density 0.009%

    No Known Activations