© 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. 78964
    Prev
    Next
    INDEX
    Explanations

    sports conferences

    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
     Kek
    -0.09
     situaciones
    -0.08
     reden
    -0.08
     상황
    -0.07
     vəzi
    -0.07
     liig
    -0.07
     Investors
    -0.07
     bg
    -0.07
     Quint
    -0.07
     administrativas
    -0.07
    POSITIVE LOGITS
    cep
    0.08
    ece
    0.08
     decid
    0.07
    Mand
    0.07
    ffc
    0.07
    ****↵
    0.07
     collaborations
    0.07
     electives
    0.07
    Lincoln
    0.07
     পালন
    0.07
    Activations Density 0.017%

    No Known Activations