© 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. 30993
    Prev
    Next
    INDEX
    Explanations

    math derivations

    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
     信
    -0.08
     子
    -0.08
     很
    -0.08
    ্চ
    -0.08
     barn
    -0.08
    ವರ
    -0.08
     bessere
    -0.07
    伦理
    -0.07
     ark
    -0.07
     cheval
    -0.07
    POSITIVE LOGITS
     previously
    0.10
     anteriormente
    0.09
     sebelumnya
    0.09
     earlier
    0.09
    Previously
    0.08
    Earlier
    0.08
     aforementioned
    0.08
    previous
    0.08
     Previously
    0.08
     discussed
    0.08
    Activations Density 0.087%

    No Known Activations