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

    Neuronpedia

    APICircuit 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. 43987
    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
     лом
    -0.08
     razor
    -0.08
     lug
    -0.08
     jub
    -0.07
    快速
    -0.07
     Romney
    -0.07
     rápido
    -0.07
     slice
    -0.07
     contains
    -0.07
     self
    -0.07
    POSITIVE LOGITS
    일보
    0.08
     barr
    0.08
     dezelfde
    0.08
    PRECATED
    0.07
    슷
    0.07
    ッ
    0.07
    辖
    0.07
    >-->↵
    0.07
     tetapi
    0.07
     kembali
    0.07
    Activations Density 0.005%

    No Known Activations