© 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. 3-RESID-POST-AA
    11. 13359
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    've
    -0.10
    Las
    -0.08
    wein
    -0.08
    вы
    -0.07
     Las
    -0.07
     mer
    -0.07
    ζει
    -0.07
     Mer
    -0.07
    mul
    -0.07
    Hallo
    -0.07
    POSITIVE LOGITS
     sprint
    0.09
     цикл
    0.08
     pursuit
    0.08
     pursuits
    0.08
     districts
    0.07
     supervised
    0.07
     заб
    0.07
     spit
    0.07
     punish
    0.07
     flooded
    0.07
    Activations Density 0.004%

    No Known Activations