© 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. 31138
    Prev
    Next
    INDEX
    Explanations

    carryback and Japanese

    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
     ordering
    -0.09
     Ordering
    -0.09
    Ordering
    -0.09
    ordering
    -0.08
    Ä
    -0.08
     waars
    -0.07
    ford
    -0.07
    ............
    -0.07
     Integration
    -0.07
     multifunction
    -0.07
    POSITIVE LOGITS
    icule
    0.08
    ेत्री
    0.08
    jük
    0.07
    omegran
    0.07
     cole
    0.07
    เตอร์
    0.07
     aşk
    0.07
    .tab
    0.07
    sec
    0.07
     sec
    0.07
    Activations Density 0.000%

    No Known Activations