© 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. 70716
    Prev
    Next
    INDEX
    Explanations

    with

    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
     hike
    -0.07
     failing
    -0.07
     focused
    -0.07
    Masked
    -0.07
     pos
    -0.07
     masker
    -0.07
    -0.06
     difficult
    -0.06
    urig
    -0.06
     parasites
    -0.06
    POSITIVE LOGITS
    cé
    0.09
     peacefully
    0.09
    أفضل
    0.08
    veal
    0.08
     customizable
    0.08
     станет
    0.08
     لدى
    0.08
     tuh
    0.08
     dac
    0.08
    rah
    0.08
    Activations Density 0.002%
    No Known Activations