© 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. 11-RESID-POST-AA
    11. 8102
    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
     sayesinde
    -0.08
    ವರು
    -0.08
    .ul
    -0.08
    arb
    -0.07
    Esk
    -0.07
     gele
    -0.07
     하
    -0.07
     pill
    -0.07
     Obl
    -0.07
     Scotts
    -0.07
    POSITIVE LOGITS
     prosperity
    0.08
    وض
    0.08
    ểu
    0.08
     patr
    0.07
     justific
    0.07
     sfe
    0.07
     aptly
    0.07
     highly
    0.07
     опера
    0.07
    不过
    0.07
    Activations Density 0.006%

    No Known Activations