© 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. 114169
    Prev
    Next
    INDEX
    Explanations

    ogonal

    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
     havia
    -0.09
     Cá
    -0.08
    гуз
    -0.08
     плюс
    -0.08
    _caption
    -0.07
    .kr
    -0.07
    තු
    -0.07
     Wang
    -0.07
     Xia
    -0.07
     Haw
    -0.07
    POSITIVE LOGITS
    cemia
    0.08
    ution
    0.07
    掉
    0.07
     transpose
    0.07
     radians
    0.07
     Jes
    0.07
    itee
    0.07
    ities
    0.07
    IMS
    0.07
     Leib
    0.07
    Activations Density 0.002%

    No Known Activations