© 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. 7-RESID-POST-AA
    11. 1359
    Prev
    Next
    INDEX
    Explanations

    prism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     امري
    -0.08
    US
    -0.08
    美国
    -0.08
     美国
    -0.08
     hortic
    -0.07
     Detroit
    -0.07
    Για
    -0.07
    USA
    -0.07
     radical
    -0.07
     meetup
    -0.07
    POSITIVE LOGITS
     psz
    0.08
     assured
    0.08
     kasih
    0.08
    첨
    0.07
     Congratulations
    0.07
    0.07
     শেষে
    0.07
     sagitt
    0.07
    bern
    0.07
    帶
    0.07
    Activations Density 0.002%
    No Known Activations