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. 109560
    Prev
    Next
    INDEX
    Explanations

    back

    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
     alkaline
    -0.08
     Victor
    -0.08
     devotees
    -0.08
     alumni
    -0.08
     Tesco
    -0.08
     образования
    -0.08
     যোগাযোগ
    -0.07
     newcomers
    -0.07
    δέ
    -0.07
    سسة
    -0.07
    POSITIVE LOGITS
    Simulation
    0.09
     simulation
    0.09
     ചരിത്ര
    0.09
     history
    0.09
     تاریخی
    0.09
    歷
    0.09
    .history
    0.08
     simulator
    0.08
    历史
    0.08
     geschiedenis
    0.08
    Activations Density 0.002%

    No Known Activations