© 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. 69931
    Prev
    Next
    INDEX
    Explanations

    actually

    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
     iss
    -0.08
     ধর
    -0.08
    ious
    -0.08
    who
    -0.08
    >I
    -0.07
    ({"
    -0.07
    699
    -0.07
    	I
    -0.07
     чыккан
    -0.07
    :I
    -0.07
    POSITIVE LOGITS
     просто
    0.09
     malah
    0.08
     наоборот
    0.08
     vielmehr
    0.08
     simply
    0.08
     typo
    0.07
     Übers
    0.07
    む
    0.07
     faute
    0.07
    骗局
    0.07
    Activations Density 0.058%

    No Known Activations