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. 15-RESID-POST-AA
    6. 19500
    Prev
    Next
    INDEX
    Explanations

    bounce

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lux
    -0.08
     "
    -0.08
     anya
    -0.07
     Tick
    -0.07
     moon
    -0.07
     Hence
    -0.07
     elephant
    -0.07
     bab
    -0.07
     Polsce
    -0.07
     vý
    -0.07
    POSITIVE LOGITS
    (Return
    0.10
    率
    0.09
     bewertet
    0.09
     Fiverr
    0.09
     Rates
    0.09
     rates
    0.09
     tasas
    0.09
     сайтов
    0.09
    률
    0.09
     ухуд
    0.09
    Activations Density 0.001%

    No Known Activations