© 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. 643
    Prev
    Next
    INDEX
    Explanations

    code

    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
     jako
    -0.09
     dissip
    -0.08
     zitten
    -0.08
    ществ
    -0.08
    Shoot
    -0.08
    不足
    -0.07
    //@
    -0.07
    criv
    -0.07
     downfall
    -0.07
     darle
    -0.07
    POSITIVE LOGITS
     玉
    0.09
    (xml
    0.09
     Mal
    0.08
     Bat
    0.08
     لا
    0.08
     Familien
    0.08
    ahana
    0.08
    (Xml
    0.08
     организация
    0.08
    ianas
    0.08
    Activations Density 0.000%

    No Known Activations