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

    Neuronpedia

    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. 25956
    Prev
    Next
    INDEX
    Explanations

    if

    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
     nyore
    -0.09
    untza
    -0.08
    want
    -0.08
     hormona
    -0.08
     enkel
    -0.08
     ukuy
    -0.08
    lige
    -0.07
    Victoria
    -0.07
     opge
    -0.07
    windigkeit
    -0.07
    POSITIVE LOGITS
    이라는
    0.08
    داع
    0.08
     provis
    0.07
     blah
    0.07
    иев
    0.07
     dozens
    0.07
    teen
    0.07
     을
    0.07
    Embora
    0.07
     بأن
    0.07
    Activations Density 0.019%

    No Known Activations