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. 119302
    Prev
    Next
    INDEX
    Explanations

    if

    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
    argon
    -0.07
    (bitmap
    -0.07
     Wave
    -0.07
    bitmap
    -0.07
     yöntem
    -0.07
     courier
    -0.07
    υ
    -0.07
     bitmap
    -0.07
     Bit
    -0.06
    וח
    -0.06
    POSITIVE LOGITS
     balancing
    0.11
     संत
    0.10
    balances
    0.10
    Balances
    0.09
     perceived
    0.09
     સંત
    0.09
     intensity
    0.09
     ബാല
    0.09
     proporcional
    0.09
     compensation
    0.09
    Activations Density 0.016%

    No Known Activations