© 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. 3-RESID-POST-AA
    11. 2783
    Prev
    Next
    INDEX
    Explanations

    اغ

    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
     Männer
    -0.08
     rolling
    -0.08
    rolled
    -0.07
     farm
    -0.07
     DER
    -0.07
     želite
    -0.07
    考试
    -0.07
    -0.07
    -li
    -0.07
     knitting
    -0.07
    POSITIVE LOGITS
    rany
    0.08
     Mitch
    0.08
     antic
    0.07
     Mueller
    0.07
     Mendes
    0.07
    640
    0.07
    590
    0.07
    nir
    0.07
     subsequently
    0.07
    तान
    0.07
    Activations Density 0.000%
    No Known Activations