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. 56224
    Prev
    Next
    INDEX
    Explanations

    language

    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
     объ
    -0.09
     parab
    -0.09
     overshadow
    -0.08
     confined
    -0.07
    жащ
    -0.07
     debajo
    -0.07
    ите
    -0.07
    การณ์
    -0.07
    per
    -0.07
     Nar
    -0.07
    POSITIVE LOGITS
    UAGE
    0.09
    -speaking
    0.09
     uc
    0.08
    交流
    0.08
     пов
    0.08
    Matter
    0.08
    achi
    0.07
     seg
    0.07
    adle
    0.07
     العربية
    0.07
    Activations Density 0.103%

    No Known Activations