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. 129781
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
    �名
    -0.09
     monopoly
    -0.08
     Monopoly
    -0.08
     philanthropic
    -0.08
     banners
    -0.08
     championships
    -0.08
     Coupon
    -0.08
     promotional
    -0.08
     bans
    -0.07
     addiction
    -0.07
    POSITIVE LOGITS
     rotated
    0.12
    rotation
    0.12
    _rotation
    0.11
     torque
    0.11
     rotation
    0.11
    _rot
    0.11
     Rotation
    0.10
    Rotation
    0.10
     rotating
    0.10
     rotates
    0.10
    Activations Density 0.010%

    No Known Activations