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. 42064
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     والر
    -0.08
     każ
    -0.07
     Johnson
    -0.07
    ruž
    -0.07
     والمؤ
    -0.07
    Johnson
    -0.07
     ഓരോ
    -0.07
     **
    -0.07
     acceptable
    -0.07
    äll
    -0.07
    POSITIVE LOGITS
    bruck
    0.08
     Seeder
    0.08
     заявил
    0.08
    mega
    0.07
     업체
    0.07
    大师
    0.07
     SBA
    0.07
     진
    0.07
    stern
    0.07
    ంపై
    0.07
    Activations Density 0.001%

    No Known Activations