© 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. 69145
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     wond
    -0.08
     fascinating
    -0.08
     tensions
    -0.07
     exercised
    -0.07
     Haben
    -0.07
    Soll
    -0.07
    уқ
    -0.07
    culos
    -0.07
     paulista
    -0.07
    pons
    -0.07
    POSITIVE LOGITS
     вообще
    0.09
     tampoco
    0.08
     hingegen
    0.07
     też
    0.07
    等等
    0.07
     sieht
    0.07
     "&
    0.07
     Swar
    0.07
     совсем
    0.07
     কেউ
    0.07
    Activations Density 0.089%

    No Known Activations