© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45349
    Prev
    Next
    INDEX
    Explanations

    Mode

    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
     frisk
    -0.07
     TED
    -0.07
     son's
    -0.07
     potens
    -0.07
     hled
    -0.07
     electric
    -0.07
     kamer
    -0.07
     brisk
    -0.07
     kth
    -0.07
     Lup
    -0.07
    POSITIVE LOGITS
    gaande
    0.08
    ள்
    0.08
    Antwort
    0.08
     فوج
    0.08
    ್ಞಾನ
    0.08
     yoxdur
    0.08
    gue
    0.07
     منهم
    0.07
    żjoni
    0.07
     จริง
    0.07
    Activations Density 0.000%

    No Known Activations