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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114279
    Prev
    Next
    INDEX
    Explanations

    worst

    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
     chunky
    -0.08
    itl
    -0.07
     supplied
    -0.07
     lacus
    -0.07
    can
    -0.07
    mer
    -0.07
     chakra
    -0.07
     devoted
    -0.07
    Cupid
    -0.07
    लेट
    -0.07
    POSITIVE LOGITS
     outcomes
    0.13
     Outcomes
    0.13
     worst
    0.12
     Worst
    0.12
     outcome
    0.12
     scenarios
    0.12
     conting
    0.11
    Worst
    0.11
     Outcome
    0.11
    enarios
    0.11
    Activations Density 0.049%

    No Known Activations