Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30504
    Prev
    Next
    INDEX
    Explanations

    seconds

    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
     toro
    -0.09
    anom
    -0.07
     strtoupper
    -0.07
    shed
    -0.07
     বড়
    -0.07
     large
    -0.07
    -English
    -0.07
     ucz
    -0.07
     messages
    -0.07
    odi
    -0.07
    POSITIVE LOGITS
    delay
    0.10
     délais
    0.10
     tiempos
    0.10
     വൈക
    0.09
    _delay
    0.09
     delay
    0.09
     वेळ
    0.09
     الزمن
    0.09
     Sekunden
    0.09
     时间
    0.09
    Activations Density 0.002%

    No Known Activations