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. 12727
    Prev
    Next
    INDEX
    Explanations

    email

    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
    🏻
    -0.09
    semos
    -0.08
    _Label
    -0.08
    alim
    -0.08
    lood
    -0.07
    ervation
    -0.07
    üml
    -0.07
    🏼
    -0.07
     Sis
    -0.07
     succession
    -0.07
    POSITIVE LOGITS
     காண
    0.09
     mellitus
    0.08
     hyvä
    0.08
     الشكل
    0.08
     나타
    0.08
     Ж
    0.08
     هد
    0.08
     Представ
    0.07
     Пред
    0.07
    .astype
    0.07
    Activations Density 0.002%

    No Known Activations