© 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 EvalsExportsinterp-engineNEWAPI 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. 114237
    Prev
    Next
    INDEX
    Explanations

    advertisements

    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
     fou
    -0.08
    గ్య
    -0.08
    456
    -0.08
    ¸
    -0.08
     steadfast
    -0.08
    াটো
    -0.08
    364
    -0.07
    ستان
    -0.07
    [Y
    -0.07
    leisten
    -0.07
    POSITIVE LOGITS
     अभियान
    0.11
     Featuring
    0.10
     campaign
    0.10
     creatives
    0.09
     cinematic
    0.09
     featuring
    0.09
     campagne
    0.09
     حملة
    0.09
     Campaign
    0.09
     slogan
    0.09
    Activations Density 0.055%

    No Known Activations