© 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. 91267
    Prev
    Next
    INDEX
    Explanations

    mega

    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
     crimin
    -0.09
     न्याय
    -0.08
     நீத
    -0.08
    osition
    -0.08
     ESG
    -0.08
     alluring
    -0.07
    /application
    -0.07
     seismic
    -0.07
     malls
    -0.07
    etur
    -0.07
    POSITIVE LOGITS
     telef
    0.09
     Gry
    0.08
     brewer
    0.08
     limón
    0.08
     Brewing
    0.08
     телеф
    0.08
    .listen
    0.08
    rechts
    0.08
     chlorine
    0.08
     Oval
    0.08
    Activations Density 0.002%

    No Known Activations