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. 12931
    Prev
    Next
    INDEX
    Explanations

    level

    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
     Mao
    -0.08
    Attendance
    -0.08
     Af
    -0.08
     bestaat
    -0.07
     besteh
    -0.07
    Tv
    -0.07
     práv
    -0.07
     attendance
    -0.07
     Tv
    -0.07
    .clean
    -0.07
    POSITIVE LOGITS
     уровне
    0.09
    IGIN
    0.08
     المستوى
    0.08
     grinding
    0.08
    elsius
    0.08
     कराने
    0.08
    ടി
    0.08
    OLAR
    0.08
     itib
    0.08
    niveau
    0.08
    Activations Density 0.008%

    No Known Activations