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. 339
    Prev
    Next
    INDEX
    Explanations

    Statistical analysis

    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
     personalizada
    -0.08
     emotion
    -0.08
     mood
    -0.08
     @(
    -0.07
     qualidade
    -0.07
    (import
    -0.07
     మె
    -0.07
     weiter
    -0.07
    Imported
    -0.07
    (operation
    -0.07
    POSITIVE LOGITS
     cé
    0.08
    LEMENT
    0.08
     Cau
    0.08
     Steen
    0.08
    ેષ
    0.08
     Ortalama
    0.07
    िष्ट
    0.07
    ्लेष
    0.07
     Gün
    0.07
     Kü
    0.07
    Activations Density 0.002%

    No Known Activations