© 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. 110800
    Prev
    Next
    INDEX
    Explanations

    media player plugins

    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
     intimacy
    -0.08
    党建
    -0.08
    Stored
    -0.08
     bombas
    -0.08
    (after
    -0.07
    Congratulations
    -0.07
     Château
    -0.07
     Mexico
    -0.07
    援
    -0.07
     übertragen
    -0.07
    POSITIVE LOGITS
    最新版
    0.11
    needed
    0.10
     installieren
    0.09
     installé
    0.09
     instalada
    0.09
     Needed
    0.09
    erst
    0.09
     nodig
    0.09
     venen
    0.09
     最新
    0.09
    Activations Density 0.007%

    No Known Activations