© 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. 45508
    Prev
    Next
    INDEX
    Explanations

    time/minutes

    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
     Sothe
    -0.08
    usen
    -0.08
     Complaint
    -0.07
     nešto
    -0.07
    073
    -0.07
     Goodbye
    -0.07
     cancellation
    -0.07
     Flaming
    -0.07
     gelungen
    -0.07
     Poste
    -0.07
    POSITIVE LOGITS
     rotations
    0.10
     releg
    0.10
    Rotation
    0.09
     rotation
    0.09
     Rotation
    0.09
     diberikan
    0.08
     нагруз
    0.08
     preseason
    0.08
    _rotation
    0.08
    球队
    0.08
    Activations Density 0.087%

    No Known Activations