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. 119372
    Prev
    Next
    INDEX
    Explanations

    them

    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
    女人
    -0.08
    acula
    -0.07
    ®
    -0.07
    ρός
    -0.07
     Nr
    -0.07
    uthorized
    -0.07
    ีน
    -0.07
    gbọ
    -0.07
    ാത്ര
    -0.07
    ®,
    -0.07
    POSITIVE LOGITS
    subscribe
    0.08
     struggling
    0.07
     പദ്ധത
    0.07
    /remove
    0.07
     Chad
    0.07
    meister
    0.07
     plans
    0.07
     मिलने
    0.07
     сможет
    0.07
    的网站
    0.07
    Activations Density 0.015%

    No Known Activations