© 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 EvalsExportsinterp-engineNEWAPI 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. 70558
    Prev
    Next
    INDEX
    Explanations

    Drake Equation

    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
    Refer
    -0.08
     diet
    -0.08
    refer
    -0.07
     it
    -0.07
    Fuse
    -0.07
     return
    -0.07
     refer
    -0.07
     tonnes
    -0.07
    Referenced
    -0.07
     Refer
    -0.07
    POSITIVE LOGITS
     civilizations
    0.10
     المدن
    0.10
    遍
    0.09
     civilization
    0.09
     حقيقة
    0.09
     Städten
    0.09
     Cities
    0.09
    cities
    0.09
    文明
    0.09
     überall
    0.09
    Activations Density 0.005%

    No Known Activations