© 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. 7-RESID-POST-AA
    11. 970
    Prev
    Next
    INDEX
    Explanations

    Words ending in ational/ional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ber
    -0.08
     elic
    -0.07
     నివ
    -0.07
     constellation
    -0.07
     unfold
    -0.07
     CET
    -0.07
    experiment
    -0.07
     unfolding
    -0.07
    试
    -0.07
    .stock
    -0.07
    POSITIVE LOGITS
     Ladder
    0.08
    iented
    0.08
     fuels
    0.07
    BG
    0.07
     Bulldog
    0.07
    piro
    0.07
     TL
    0.07
     Boc
    0.07
    วน
    0.07
     Baton
    0.07
    Activations Density 0.051%

    No Known Activations