© 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. 47991
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     fonctionnalités
    -0.08
     административ
    -0.08
     funcionalidades
    -0.08
     functionality
    -0.08
     functionalities
    -0.08
     DLL
    -0.08
     Debit
    -0.08
    ophile
    -0.08
    iów
    -0.08
     administratif
    -0.08
    POSITIVE LOGITS
     বক্ত
    0.09
     Humans
    0.09
     beautifully
    0.09
     Nobel
    0.09
     TED
    0.09
     overtu
    0.09
     convain
    0.08
    формация
    0.08
     Childhood
    0.08
     nonprofits
    0.08
    Activations Density 0.009%

    No Known Activations