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. 19461
    Prev
    Next
    INDEX
    Explanations

    "additional" in other languages

    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
     mean
    -0.07
     preceded
    -0.07
    ူး
    -0.07
     Tant
    -0.06
    mean
    -0.06
    -0.06
     navig
    -0.06
    �
    -0.06
     properties
    -0.06
     Boutique
    -0.06
    POSITIVE LOGITS
     adicional
    0.13
     zusätzlichen
    0.12
     adicionais
    0.11
     incluir
    0.11
     дополнитель
    0.11
     zusätz
    0.11
     adicionales
    0.11
     zusätzliche
    0.11
     дополнительные
    0.11
    Additional
    0.11
    Activations Density 0.197%

    No Known Activations