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. 88132
    Prev
    Next
    INDEX
    Explanations

    County, parish

    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
     خانو
    -0.10
     Twain
    -0.09
    シリーズ
    -0.08
     denim
    -0.08
    AYOUT
    -0.08
    بور
    -0.08
    мос
    -0.08
     henkil
    -0.08
     Barnes
    -0.08
    穴
    -0.08
    POSITIVE LOGITS
     acknowledge
    0.08
    .the
    0.07
    ,the
    0.07
     urgent
    0.07
     transport
    0.07
     auton
    0.07
    }}
    0.07
     swimming
    0.07
    Swimming
    0.07
     prevail
    0.07
    Activations Density 0.029%

    No Known Activations