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. 60533
    Prev
    Next
    INDEX
    Explanations

    1

    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
    kerk
    -0.08
    klass
    -0.08
     intended
    -0.08
    ikler
    -0.08
    ’nin
    -0.07
    iramente
    -0.07
    -shell
    -0.07
    ysen
    -0.07
    engk
    -0.07
     қалған
    -0.07
    POSITIVE LOGITS
    兑换
    0.10
     translating
    0.09
     converting
    0.09
    一卡
    0.09
    转换
    0.09
     conversion
    0.09
     convertir
    0.09
    一码
    0.09
     roughly
    0.08
     Conversion
    0.08
    Activations Density 0.032%

    No Known Activations