© 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. 19-RESID-POST-AA
    11. 18451
    Prev
    Next
    INDEX
    Explanations

    lacquer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ningi
    -0.09
    க்கு
    -0.09
     dreamy
    -0.08
     typische
    -0.08
     bubbly
    -0.08
    ুটি
    -0.08
    ்ந
    -0.08
    lickr
    -0.08
     juicy
    -0.08
    spě
    -0.08
    POSITIVE LOGITS
     demands
    0.08
     الأد
    0.07
     utensils
    0.07
    ാല
    0.07
     ನ್ಯಾಯ
    0.07
     trees
    0.07
     black
    0.07
    ერდ
    0.07
    ത്തിന്റെ
    0.07
    ალდ
    0.07
    Activations Density 0.000%

    No Known Activations