© 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. 111385
    Prev
    Next
    INDEX
    Explanations

    Rhino

    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
     stimulant
    -0.08
     Uzbekistan
    -0.08
     roman
    -0.08
     celebration
    -0.08
     Mer
    -0.07
     Uzbek
    -0.07
     Stephanie
    -0.07
     whatever
    -0.07
     Pearson
    -0.07
     вступ
    -0.07
    POSITIVE LOGITS
     segíts
    0.09
     GUILayout
    0.08
     manipulate
    0.08
     discre
    0.08
     groundbreaking
    0.08
    院
    0.08
    神器
    0.08
    \Builder
    0.08
     looph
    0.07
     manipulation
    0.07
    Activations Density 0.001%

    No Known Activations