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. 7-RESID-POST-AA
    6. 130981
    Prev
    Next
    INDEX
    Explanations

    OpenGL texture parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Manor
    -0.10
     Kont
    -0.09
     beek
    -0.08
     aburr
    -0.07
    371
    -0.07
     Yam
    -0.07
     Сп
    -0.07
     reproduc
    -0.07
     Yard
    -0.07
    ortar
    -0.07
    POSITIVE LOGITS
     fechado
    0.07
    訪
    0.07
     gebruiken
    0.07
     shades
    0.07
     säger
    0.07
     kleuren
    0.07
     realizará
    0.07
    tected
    0.07
    ין
    0.07
     spontane
    0.07
    Activations Density 0.001%

    No Known Activations