© 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. 111146
    Prev
    Next
    INDEX
    Explanations

    Removal or avoidance

    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
    ../
    -0.08
    orro
    -0.07
     defending
    -0.07
    elongs
    -0.07
     Amelia
    -0.07
     Myself
    -0.07
    유
    -0.07
    hus
    -0.07
    "),
↵
    -0.07
    粤
    -0.07
    POSITIVE LOGITS
     outright
    0.19
    完全
    0.12
    彻
    0.11
     downright
    0.11
     overhaul
    0.11
     полностью
    0.10
     tamamen
    0.10
     úpl
    0.10
     drastic
    0.10
     સંપૂર્ણ
    0.10
    Activations Density 0.191%

    No Known Activations