© 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. 68923
    Prev
    Next
    INDEX
    Explanations

    chrome

    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
    섭
    -0.08
    nale
    -0.07
     =="
    -0.07
     cooper
    -0.07
     resc
    -0.07
     diaria
    -0.07
     Via
    -0.07
    hab
    -0.07
     recur
    -0.07
    otif
    -0.07
    POSITIVE LOGITS
     ضد
    0.08
    dew
    0.08
    well
    0.08
     follicles
    0.08
     filings
    0.08
     aza
    0.08
    eci
    0.07
     fingers
    0.07
    finger
    0.07
     tongue
    0.07
    Activations Density 0.002%

    No Known Activations