© 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. 99667
    Prev
    Next
    INDEX
    Explanations

    style/格

    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
     통한
    -0.07
     anne
    -0.07
     chaleur
    -0.07
    ുക
    -0.07
     exp
    -0.07
     buah
    -0.07
     rejuven
    -0.07
     batería
    -0.07
     recharge
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     ег
    0.09
     hochwert
    0.08
     trocken
    0.08
    ewel
    0.08
    ವಾದ
    0.08
     memoir
    0.08
     gritty
    0.08
     Gart
    0.08
     lama
    0.08
    ,count
    0.08
    Activations Density 0.006%

    No Known Activations