© 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. 113552
    Prev
    Next
    INDEX
    Explanations

    Russian technical documents

    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
     definit
    -0.09
     miesię
    -0.08
     ____
    -0.07
     toont
    -0.07
     coef
    -0.07
     δεί
    -0.07
     MSN
    -0.07
     substant
    -0.07
     afirm
    -0.07
     vestib
    -0.07
    POSITIVE LOGITS
    Technical
    0.08
     dying
    0.08
     equipment
    0.08
     ká
    0.08
    流程
    0.07
     Genuss
    0.07
     pipeline
    0.07
     vibe
    0.07
    Kim
    0.07
     cars
    0.07
    Activations Density 0.009%

    No Known Activations