© 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. 78114
    Prev
    Next
    INDEX
    Explanations

    lists and hyphens

    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
     men's
    -0.08
    -ha
    -0.07
    owi
    -0.07
     rere
    -0.07
    enie
    -0.07
    ,:)
    -0.07
     POV
    -0.07
    שה
    -0.07
     dét
    -0.07
     Pav
    -0.07
    POSITIVE LOGITS
    0.08
     ----------↵
    0.07
     Corte
    0.07
     fel
    0.07
     كنت
    0.07
     """↵↵
    0.07
    ----↵
    0.07
     والس
    0.07
    —↵↵
    0.07
     Dor
    0.07
    Activations Density 0.062%
    No Known Activations