© 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. 63892
    Prev
    Next
    INDEX
    Explanations

    van

    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
     fatig
    -0.09
     tiring
    -0.08
     посет
    -0.08
    及时
    -0.08
    Visit
    -0.08
    没
    -0.08
     fleet
    -0.08
     visitar
    -0.07
     visite
    -0.07
     visiting
    -0.07
    POSITIVE LOGITS
     встав
    0.09
    .ends
    0.09
    াফল
    0.08
    exchange
    0.08
    -format
    0.08
     نهاية
    0.08
     ends
    0.08
     format
    0.08
     đoạn
    0.08
    	format
    0.07
    Activations Density 0.142%

    No Known Activations