© 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. 3-RESID-POST-AA
    11. 3079
    Prev
    Next
    INDEX
    Explanations

    然

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bren
    -0.08
     clay
    -0.08
     ponder
    -0.08
     Clay
    -0.08
    pragma
    -0.07
    ynku
    -0.07
     ум
    -0.07
     चिक
    -0.07
     absoluto
    -0.07
    ignite
    -0.07
    POSITIVE LOGITS
     Successfully
    0.08
    زع
    0.08
    પૂ
    0.08
    ('[
    0.08
    0.07
     올라
    0.07
    pem
    0.07
     الر
    0.07
    વર
    0.07
     뛰
    0.07
    Activations Density 0.001%
    No Known Activations