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

    Neuronpedia

    Jacobian LensNEW
    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. 64027
    Prev
    Next
    INDEX
    Explanations

    notation

    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
     diminish
    -0.08
     adversely
    -0.08
     ധ
    -0.08
     Vert
    -0.08
    -0.07
     νέ
    -0.07
     coming
    -0.07
     diminuir
    -0.07
     Belgium
    -0.07
     atmosfera
    -0.07
    POSITIVE LOGITS
    linky
    0.09
    ladı
    0.09
     Lenn
    0.08
    gé
    0.08
     algae
    0.08
     Bracelet
    0.08
     Blake
    0.08
    angeb
    0.07
     epoxy
    0.07
    anges
    0.07
    Activations Density 0.001%
    No Known Activations