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. 113974
    Prev
    Next
    INDEX
    Explanations

    sports tournaments

    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
     tabletop
    -0.08
     trist
    -0.08
     vocab
    -0.08
    terior
    -0.07
     DMV
    -0.07
     Kafka
    -0.07
     നടത്തി
    -0.07
     firme
    -0.07
    andaş
    -0.07
     DAO
    -0.07
    POSITIVE LOGITS
     pairing
    0.10
    (seed
    0.09
     seed
    0.09
     strength
    0.09
    _seed
    0.09
     elite
    0.08
     matchup
    0.08
     playoff
    0.08
    (assign
    0.08
     senior
    0.08
    Activations Density 0.011%

    No Known Activations