Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49205
    Prev
    Next
    INDEX
    Explanations

    vertebral body/body parts

    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
     cadence
    -0.07
     pur
    -0.07
    .people
    -0.07
    Nc
    -0.07
     Neto
    -0.07
     gồm
    -0.07
     hord
    -0.07
    .choice
    -0.07
     xem
    -0.07
    模式
    -0.07
    POSITIVE LOGITS
     déplac
    0.09
     Sharon
    0.08
     fich
    0.08
     आग
    0.08
     FSC
    0.08
     Gonzalez
    0.07
     '..
    0.07
    镜
    0.07
    urat
    0.07
     price
    0.07
    Activations Density 0.004%

    No Known Activations