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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 50181
    Prev
    Next
    INDEX
    Explanations

    الن

    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
     appearing
    -0.08
     anciennes
    -0.07
    ergarten
    -0.07
    ancienne
    -0.07
     Both
    -0.07
     embeds
    -0.07
    ateful
    -0.07
    AYER
    -0.07
    rossover
    -0.07
    -0.07
    POSITIVE LOGITS
    م
    0.11
    عيم
    0.10
    ّه
    0.09
    ظم
    0.09
    طاق
    0.09
    َّه
    0.09
    ُّ
    0.09
    شرات
    0.09
    َّ
    0.08
     múlt
    0.08
    Activations Density 0.001%

    No Known Activations