© 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. 24879
    Prev
    Next
    INDEX
    Explanations

    negations

    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
    erein
    -0.09
     entstand
    -0.07
     Erg
    -0.07
    jumlah
    -0.07
    er
    -0.07
    ，又
    -0.07
     Geneva
    -0.07
    fügung
    -0.07
     führte
    -0.07
    elon
    -0.07
    POSITIVE LOGITS
    ല്ല
    0.08
    ാ
    0.08
    Webpack
    0.08
     intim
    0.08
     raka
    0.08
     seco
    0.08
    Outside
    0.08
     sở
    0.07
    Except
    0.07
    ですが
    0.07
    Activations Density 0.055%

    No Known Activations