© 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. 70038
    Prev
    Next
    INDEX
    Explanations

    keys and encoded messages

    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
     ej
    -0.08
     écriv
    -0.08
     iu
    -0.08
     Tat
    -0.08
     inflated
    -0.08
     Handicap
    -0.08
     FC
    -0.08
     eup
    -0.07
    営
    -0.07
     admi
    -0.07
    POSITIVE LOGITS
    钥
    0.13
    匙
    0.11
     clés
    0.10
    hole
    0.10
    /key
    0.10
    鍵
    0.10
     доступа
    0.10
     clé
    0.09
    窍
    0.09
     కీల
    0.09
    Activations Density 0.019%

    No Known Activations