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. 113875
    Prev
    Next
    INDEX
    Explanations

    lichens, refrigerants, q&a

    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
    cap
    -0.08
     gifts
    -0.08
    كل
    -0.08
     Prophet
    -0.08
    stories
    -0.07
     penuh
    -0.07
    duplicates
    -0.07
     Floyd
    -0.07
    ogly
    -0.07
     партнер
    -0.07
    POSITIVE LOGITS
     نب
    0.09
     Χ
    0.08
    Dispatch
    0.08
     több
    0.08
     température
    0.07
     steuer
    0.07
     Gibraltar
    0.07
    rée
    0.07
    BRE
    0.07
     temperatura
    0.07
    Activations Density 0.003%

    No Known Activations