© 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. 8133
    Prev
    Next
    INDEX
    Explanations

    finance and settlement

    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
     ecosystem
    -0.08
     predicted
    -0.08
     આગ
    -0.08
    Org
    -0.08
    ross
    -0.07
    ibu
    -0.07
     anticipated
    -0.07
    .fore
    -0.07
    erves
    -0.07
    edu
    -0.07
    POSITIVE LOGITS
     realization
    0.09
     realiz
    0.09
    /google
    0.08
     reka
    0.08
     tensorflow
    0.08
     dren
    0.08
     Faça
    0.08
    گار
    0.08
    -login
    0.08
     realise
    0.08
    Activations Density 0.002%

    No Known Activations