Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112762
    Prev
    Next
    INDEX
    Explanations

    ribbon

    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
     stranger
    -0.07
    lego
    -0.07
    ivatives
    -0.07
    allar
    -0.07
     generate
    -0.07
     exile
    -0.07
    Aa
    -0.07
     Egg
    -0.07
     textbooks
    -0.07
     Anat
    -0.07
    POSITIVE LOGITS
     dài
    0.09
     Bianca
    0.08
     పొ
    0.08
     inse
    0.08
    ്ധ
    0.08
     Mits
    0.08
     kết
    0.07
    stick
    0.07
     waived
    0.07
     Sty
    0.07
    Activations Density 0.002%

    No Known Activations