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. 78529
    Prev
    Next
    INDEX
    Explanations

    overdoses

    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
     genom
    -0.08
     musim
    -0.08
    _catalog
    -0.08
    <Row
    -0.08
    роде
    -0.08
     netjes
    -0.08
     lett
    -0.08
    ondere
    -0.07
    .Generated
    -0.07
     ген
    -0.07
    POSITIVE LOGITS
     overdose
    0.15
     poisoning
    0.11
     intox
    0.11
     seizure
    0.10
     opioid
    0.09
     toxicity
    0.09
     addiction
    0.09
     sedation
    0.09
     withdrawal
    0.09
     suicidal
    0.09
    Activations Density 0.011%

    No Known Activations