© 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. 31599
    Prev
    Next
    INDEX
    Explanations

    fixed

    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
     ultra
    -0.08
     designing
    -0.08
     infrastruct
    -0.08
     Holland
    -0.08
     لأ
    -0.07
     extremely
    -0.07
     UB
    -0.07
     Ultra
    -0.07
    hhh
    -0.07
    uluş
    -0.07
    POSITIVE LOGITS
    0.08
    出版社
    0.08
     동
    0.08
    cash
    0.08
    ipc
    0.08
     wasnt
    0.08
    _Player
    0.08
     Donna
    0.08
     bluff
    0.08
     動
    0.08
    Activations Density 0.000%
    No Known Activations