© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94741
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    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
     eksp
    -0.08
     Здесь
    -0.07
    ขั้น
    -0.07
    으면
    -0.07
     herb
    -0.07
     шаб
    -0.07
     అలాగే
    -0.07
     chop
    -0.07
     folding
    -0.07
     nämlich
    -0.07
    POSITIVE LOGITS
     awarded
    0.08
    Combat
    0.08
     Fighters
    0.08
     পুর
    0.08
     Award
    0.07
     tohoto
    0.07
    Bless
    0.07
     Moj
    0.07
     teus
    0.07
    atts
    0.07
    Activations Density 0.009%

    No Known Activations