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. 78677
    Prev
    Next
    INDEX
    Explanations

    Family-based therapy

    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
     kl
    -0.08
     මු
    -0.08
     absor
    -0.08
     വഴ
    -0.08
     לאורך
    -0.07
     ומה
    -0.07
    .Down
    -0.07
     doing
    -0.07
     throttle
    -0.07
     intersection
    -0.07
    POSITIVE LOGITS
     aam
    0.08
     Técnica
    0.08
    怒
    0.08
     Pern
    0.08
    ہم
    0.08
    箱
    0.08
     علاج
    0.08
    pst
    0.07
    Inp
    0.07
     troubles
    0.07
    Activations Density 0.002%

    No Known Activations