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. 49301
    Prev
    Next
    INDEX
    Explanations

    mechanics

    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
     vaping
    -0.08
     biotechnology
    -0.08
    gevity
    -0.08
    icemail
    -0.08
     웃
    -0.08
    .learning
    -0.08
    Emoji
    -0.07
     Pinot
    -0.07
    県
    -0.07
     gummies
    -0.07
    POSITIVE LOGITS
     Verlet
    0.12
    inematics
    0.11
    运动
    0.10
    _motion
    0.10
     trajectories
    0.10
     Forces
    0.10
     motion
    0.10
     fuerzas
    0.09
     Kräfte
    0.09
     tracer
    0.09
    Activations Density 0.011%

    No Known Activations