© 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. 112406
    Prev
    Next
    INDEX
    Explanations

    matrices

    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
     anders
    -0.08
    <>↵
    -0.08
    �
    -0.08
    商业
    -0.07
    ???↵
    -0.07
     commercial
    -0.07
    żeń
    -0.07
     슬
    -0.07
    Clicks
    -0.07
     azúcar
    -0.07
    POSITIVE LOGITS
    र्ण
    0.08
     aufgeh
    0.08
     terapia
    0.08
     карто
    0.07
    naa
    0.07
     আন্ত
    0.07
    -transparent
    0.07
    ried
    0.07
     evoc
    0.07
     mode
    0.07
    Activations Density 0.004%

    No Known Activations