© 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. 1439
    Prev
    Next
    INDEX
    Explanations

    minor/or

    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
     metaphor
    -0.08
     myth
    -0.08
    онов
    -0.08
     Scotts
    -0.08
     Kond
    -0.08
     dunes
    -0.08
     ос
    -0.08
    атов
    -0.07
     Apothe
    -0.07
     Barton
    -0.07
    POSITIVE LOGITS
     sze
    0.08
    删除
    0.08
    中华人民共和国
    0.08
     évalu
    0.07
    .CASCADE
    0.07
    Calculator
    0.07
    调查
    0.07
    eselect
    0.07
     evalu
    0.07
     correspondiente
    0.07
    Activations Density 0.002%

    No Known Activations