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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 78061
    Prev
    Next
    INDEX
    Explanations

    shader code

    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
     his
    -0.09
     pastries
    -0.08
     gel
    -0.08
     gener
    -0.08
     mensen
    -0.08
     people
    -0.07
     keg
    -0.07
     examin
    -0.07
     jene
    -0.07
     jener
    -0.07
    POSITIVE LOGITS
     бағдарлам
    0.10
    одатель
    0.09
    组选
    0.09
    训
    0.08
     Nicaragua
    0.08
    (utils
    0.08
     iface
    0.08
    ាប់
    0.08
     �
    0.08
     빨
    0.08
    Activations Density 0.001%

    No Known Activations