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. 43485
    Prev
    Next
    INDEX
    Explanations

    code snippets and queries

    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
     מראש
    -0.09
    -design
    -0.08
     cultured
    -0.08
    ాశ
    -0.08
     Dhabi
    -0.08
     گست
    -0.08
     surveying
    -0.07
     nerves
    -0.07
     Holy
    -0.07
     социал
    -0.07
    POSITIVE LOGITS
     clause
    0.12
     cláus
    0.12
    WHERE
    0.11
     predicates
    0.11
     criteria
    0.11
     criterion
    0.11
     Criteria
    0.11
    Clause
    0.11
     WHERE
    0.10
     Criterion
    0.10
    Activations Density 0.015%

    No Known Activations