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. 76605
    Prev
    Next
    INDEX
    Explanations

    id

    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
     olduğu
    -0.08
     Target
    -0.08
     tendance
    -0.07
     [&](
    -0.07
     fonctionner
    -0.07
     sätt
    -0.07
     класса
    -0.07
    Cls
    -0.07
     cls
    -0.07
     cren
    -0.07
    POSITIVE LOGITS
    index
    0.09
    Aw
    0.08
    elu
    0.08
    first
    0.08
    labels
    0.08
    elapsed
    0.08
     awareness
    0.08
    EL
    0.08
    emun
    0.08
    _EXP
    0.07
    Activations Density 0.001%

    No Known Activations