© 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 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. 112548
    Prev
    Next
    INDEX
    Explanations

    thermal

    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
     инт
    -0.08
     meinte
    -0.08
    'ed
    -0.08
    _plot
    -0.07
    ets
    -0.07
    he
    -0.07
     सिक
    -0.07
    interactive
    -0.07
     cinque
    -0.07
     Plot
    -0.07
    POSITIVE LOGITS
     Actually
    0.08
    rocket
    0.08
    ម្�
    0.08
     aprovechar
    0.07
     Avec
    0.07
     龙
    0.07
     Aprove
    0.07
    其实
    0.07
    [list
    0.07
     Deluxe
    0.07
    Activations Density 0.002%

    No Known Activations