© 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. 3-RESID-POST-AA
    11. 13352
    Prev
    Next
    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    916
    -0.08
     elector
    -0.08
     workloads
    -0.08
    Кроме
    -0.08
     precious
    -0.07
     सहित
    -0.07
     radioactive
    -0.07
    915
    -0.07
    special
    -0.07
    ต่ำ
    -0.07
    POSITIVE LOGITS
     anomaly
    0.08
     mol
    0.08
     Hele
    0.08
    gi
    0.07
     пом
    0.07
     spindle
    0.07
     Hy
    0.07
     Twilight
    0.07
     Personalized
    0.07
    -caption
    0.07
    Activations Density 0.003%

    No Known Activations