© 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. 11-RESID-POST-AA
    11. 69735
    Prev
    Next
    INDEX
    Explanations

    👉

    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
    책
    -0.08
     bers
    -0.08
     literals
    -0.08
    lectic
    -0.08
     illness
    -0.07
     meadow
    -0.07
     Lion
    -0.07
     Gilles
    -0.07
     whe
    -0.07
     flu
    -0.07
    POSITIVE LOGITS
    🏼
    0.29
    🏻
    0.26
    起来
    0.08
     Samuel
    0.07
    ćih
    0.07
    Fk
    0.07
    赖
    0.07
     Frame
    0.07
    伟
    0.06
    ತೆಗೆ
    0.06
    Activations Density 0.002%

    No Known Activations