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. 61027
    Prev
    Next
    INDEX
    Explanations

    limit

    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
    etched
    -0.09
    点击
    -0.08
    消费者
    -0.07
     transcription
    -0.07
    scribers
    -0.07
     subscribers
    -0.07
     atm
    -0.07
    叫
    -0.07
    -filled
    -0.07
    ARENT
    -0.07
    POSITIVE LOGITS
     hebt
    0.08
    ுள்ளார்
    0.08
     UPS
    0.08
    racha
    0.08
    money
    0.08
    نسي
    0.07
     सिं
    0.07
    raichte
    0.07
    -Bo
    0.07
     courrier
    0.07
    Activations Density 0.000%

    No Known Activations