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. 52910
    Prev
    Next
    INDEX
    Explanations

    their

    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
     backyard
    -0.08
    ieces
    -0.08
     wetlands
    -0.07
     regained
    -0.07
     времена
    -0.07
    ایه
    -0.07
    그래
    -0.07
    验
    -0.07
     скорость
    -0.07
     sacs
    -0.07
    POSITIVE LOGITS
     אחרי
    0.12
    踪
    0.11
     lī
    0.11
     Trails
    0.10
     suit
    0.09
     примеру
    0.09
     perkembangan
    0.08
     развитию
    0.08
     trail
    0.08
    规律
    0.08
    Activations Density 0.080%

    No Known Activations