© 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. 111298
    Prev
    Next
    INDEX
    Explanations

    triangle

    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
     скач
    -0.08
     рамках
    -0.08
     dinosaur
    -0.08
     UNIX
    -0.08
     کړ
    -0.07
     naik
    -0.07
     bangs
    -0.07
     Gericht
    -0.07
    מו
    -0.07
     качестве
    -0.07
    POSITIVE LOGITS
    中的
    0.08
    centric
    0.08
    .databinding
    0.08
    Conse
    0.07
    irror
    0.07
     originales
    0.07
     原
    0.07
    holung
    0.07
    irr
    0.07
    রের
    0.07
    Activations Density 0.023%

    No Known Activations