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

    Neuronpedia

    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. 68505
    Prev
    Next
    INDEX
    Explanations

    Alternatives or different circumstances

    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
    .bold
    -0.08
    dots
    -0.08
    bold
    -0.08
    *cos
    -0.07
    <typename
    -0.07
     création
    -0.07
    jong
    -0.07
    *sin
    -0.07
     Correction
    -0.07
    ,*
    -0.07
    POSITIVE LOGITS
     alone
    0.10
     وحد
    0.10
     Alone
    0.09
     عس
    0.09
     ماش
    0.09
     alene
    0.09
     अके
    0.08
     unmittelbar
    0.08
    Permit
    0.08
     önü
    0.08
    Activations Density 0.053%

    No Known Activations