© 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. 111491
    Prev
    Next
    INDEX
    Explanations

    IP address

    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
     HALF
    -0.08
    INTER
    -0.08
     хран
    -0.08
     graded
    -0.08
     QRect
    -0.08
    LING
    -0.07
     cropped
    -0.07
     хранения
    -0.07
    _SCROLL
    -0.07
     союз
    -0.07
    POSITIVE LOGITS
     selfie
    0.09
     anonymously
    0.09
     bloggers
    0.09
    网上
    0.09
     festgestellt
    0.08
     websites
    0.08
     Google's
    0.08
     آنلاین
    0.08
    在线
    0.08
    redirect
    0.08
    Activations Density 0.006%

    No Known Activations