© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91839
    Prev
    Next
    INDEX
    Explanations

    Trajectory and paths

    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
     Hoe
    -0.08
    门
    -0.08
    öglich
    -0.07
     اس
    -0.07
     باب
    -0.07
    🏼
    -0.07
    .defaults
    -0.07
    annte
    -0.07
    .FE
    -0.07
     leistungs
    -0.07
    POSITIVE LOGITS
     trajectory
    0.16
     trajectories
    0.16
    trajectory
    0.14
    Trajectory
    0.13
    轨
    0.12
     trajetória
    0.11
     traject
    0.11
     paths
    0.10
    traj
    0.10
     traj
    0.10
    Activations Density 0.017%

    No Known Activations