© 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. 75666
    Prev
    Next
    INDEX
    Explanations

    contracts and legal documents

    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
     televisão
    -0.10
     Achievement
    -0.08
     televisión
    -0.08
    -Mobile
    -0.08
     Sprite
    -0.08
     Pokemon
    -0.08
     hue
    -0.08
     التلف
    -0.08
    テレビ
    -0.08
     eternal
    -0.08
    POSITIVE LOGITS
     drafting
    0.15
     drafted
    0.14
     cláus
    0.13
     réd
    0.13
     clauses
    0.13
     drafts
    0.13
    Draft
    0.12
     юрид
    0.12
     negociar
    0.12
     amendments
    0.12
    Activations Density 0.065%

    No Known Activations