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. 15-RESID-POST-AA
    6. 18900
    Prev
    Next
    INDEX
    Explanations

    metadata

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adolescent
    -0.08
    adi
    -0.08
     polarized
    -0.08
     ทั้ง
    -0.07
     ضد
    -0.07
     Rounded
    -0.07
    خاص
    -0.07
     عملي
    -0.07
     recharge
    -0.07
    ترض
    -0.07
    POSITIVE LOGITS
     metadata
    0.20
    .metadata
    0.17
    metadata
    0.17
     Metadata
    0.17
    (metadata
    0.16
    _metadata
    0.16
    Metadata
    0.15
     정보를
    0.13
     bookkeeping
    0.13
     informacje
    0.12
    Activations Density 0.042%

    No Known Activations