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. 3-RESID-POST-AA
    6. 2024
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mileage
    -0.08
     Gunn
    -0.07
    _RT
    -0.07
    Kick
    -0.07
     �
    -0.07
     decimals
    -0.07
    anen
    -0.07
     छुट
    -0.07
     breaths
    -0.07
     zgod
    -0.07
    POSITIVE LOGITS
     firsthand
    0.08
     تكن
    0.08
     стоит
    0.08
     меня
    0.07
    teen
    0.07
    科技
    0.07
     اس
    0.07
     fortune
    0.07
     الباحث
    0.07
     каждого
    0.07
    Activations Density 0.127%

    No Known Activations