© 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. 68306
    Prev
    Next
    INDEX
    Explanations

    etc

    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
     neut
    -0.08
     decom
    -0.08
     এছ
    -0.08
     Bazaar
    -0.07
     descont
    -0.07
    umik
    -0.07
     fome
    -0.07
    _sz
    -0.07
    _al
    -0.07
    ичь
    -0.07
    POSITIVE LOGITS
     milieu
    0.08
     जाते
    0.08
    ាម
    0.07
     Wunder
    0.07
     obsessive
    0.07
    0.07
     spaghetti
    0.07
    으며
    0.07
    الغ
    0.07
    �
    0.07
    Activations Density 0.033%

    No Known Activations