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. 105958
    Prev
    Next
    INDEX
    Explanations

    about

    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
     site's
    -0.08
     siguiendo
    -0.08
    Chile
    -0.08
    SALE
    -0.07
    achal
    -0.07
    ודי
    -0.07
    ודים
    -0.07
     reduct
    -0.07
    Skeleton
    -0.07
     kupitia
    -0.07
    POSITIVE LOGITS
    imate
    0.08
    
    0.08
    vine
    0.07
     "\"
    0.07
    =\'
    0.07
     pp
    0.07
    _anim
    0.07
     ganhou
    0.07
     Capricorn
    0.07
    ucun
    0.07
    Activations Density 0.025%

    No Known Activations