© 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. 47723
    Prev
    Next
    INDEX
    Explanations

    up

    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
    مدينة
    -0.08
     déplacements
    -0.07
    类似
    -0.07
    到
    -0.07
    וקים
    -0.07
    èques
    -0.07
    bas
    -0.07
    러운
    -0.07
    其他
    -0.07
    -0.07
    POSITIVE LOGITS
     cockpit
    0.09
     halfway
    0.09
     والص
    0.08
     käyttö
    0.08
     Возможно
    0.08
     सूर्य
    0.08
     spann
    0.08
     వెంట
    0.08
    olas
    0.08
     séparation
    0.08
    Activations Density 0.002%
    No Known Activations