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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1219
    Prev
    Next
    INDEX
    Explanations

    image

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baan
    -0.09
    Kl
    -0.08
    ÜR
    -0.08
     υπ
    -0.08
    ూర్
    -0.08
    Alchemy
    -0.08
    рик
    -0.08
     elit
    -0.08
     dobre
    -0.07
     JAN
    -0.07
    POSITIVE LOGITS
     siyaas
    0.07
     निध
    0.07
     ضمن
    0.07
     bekende
    0.07
    -linked
    0.07
     thrilled
    0.07
     rewarded
    0.07
     success
    0.07
     kijken
    0.07
     finances
    0.07
    Activations Density 0.000%

    No Known Activations