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. 119290
    Prev
    Next
    INDEX
    Explanations

    Hallucinations/Drug induced states

    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
     footer
    -0.09
     FOOT
    -0.09
     pixels
    -0.08
    порт
    -0.07
    Formats
    -0.07
     apoyo
    -0.07
     estas
    -0.07
     colis
    -0.07
    嫁
    -0.07
    -0.07
    POSITIVE LOGITS
     intox
    0.14
     cognitive
    0.14
     sedation
    0.13
     delir
    0.13
     Cognitive
    0.13
     наркот
    0.13
     trance
    0.12
    derall
    0.12
     ADHD
    0.12
     caffeine
    0.12
    Activations Density 0.095%

    No Known Activations