© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 113741
    Prev
    Next
    INDEX
    Explanations

    code

    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
     resid
    -0.08
     vac
    -0.08
     empt
    -0.07
    Warnings
    -0.07
     autonomy
    -0.07
     무료
    -0.07
     Bedford
    -0.07
     boils
    -0.07
     restricting
    -0.07
     retreats
    -0.07
    POSITIVE LOGITS
     alphabetical
    0.11
     reordered
    0.10
    alphabet
    0.09
    排序
    0.09
    -order
    0.09
     лес
    0.09
     alfabet
    0.09
    curve
    0.09
     curve
    0.09
    processed
    0.09
    Activations Density 0.004%

    No Known Activations