© 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. 45597
    Prev
    Next
    INDEX
    Explanations

    {"

    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
     verzam
    -0.08
    软件下载
    -0.08
     afspraak
    -0.08
     laboratoire
    -0.08
    teurs
    -0.08
     kone
    -0.08
    Numero
    -0.07
     appetite
    -0.07
    さら
    -0.07
    ลาก
    -0.07
    POSITIVE LOGITS
    amin
    0.08
     Zoe
    0.07
    Dann
    0.07
     Seq
    0.07
     ocasion
    0.07
     predefined
    0.07
     ideale
    0.07
     ಹೊ
    0.07
    0.07
     glaring
    0.07
    Activations Density 0.006%
    No Known Activations