© 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. 29431
    Prev
    Next
    INDEX
    Explanations

    meant to

    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
    DM
    -0.09
     betrekking
    -0.08
    ваются
    -0.08
    بی
    -0.08
     Thema
    -0.08
    Normalized
    -0.07
    အား
    -0.07
    ền
    -0.07
    avae
    -0.07
    DDR
    -0.07
    POSITIVE LOGITS
     seng
    0.09
     שאני
    0.09
     usted
    0.08
     vulner
    0.08
     cbd
    0.08
    ög
    0.07
     harm
    0.07
     uncomfortable
    0.07
     પોત
    0.07
     Vlaanderen
    0.07
    Activations Density 0.002%

    No Known Activations