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. 76486
    Prev
    Next
    INDEX
    Explanations

    Shamanism

    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
    озя
    -0.08
     bicarbon
    -0.08
     peripheral
    -0.08
     sitcom
    -0.08
     hydrochlor
    -0.08
    uced
    -0.08
     picturesque
    -0.08
     grapefruit
    -0.07
     manor
    -0.07
    Charles
    -0.07
    POSITIVE LOGITS
     ചടങ്ങ
    0.13
     tribal
    0.12
     rituals
    0.12
     ceremonies
    0.12
     Ceremony
    0.12
     chanting
    0.11
     ceremony
    0.11
     chants
    0.11
     ceremon
    0.11
     Tribal
    0.11
    Activations Density 0.041%

    No Known Activations