© 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. 2879
    Prev
    Next
    INDEX
    Explanations

    -shaped

    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
    hoo
    -0.07
     liệu
    -0.07
    eti
    -0.07
     HAM
    -0.07
    container
    -0.07
     mui
    -0.07
    �
    -0.07
     tequila
    -0.07
     brigade
    -0.07
     APO
    -0.07
    POSITIVE LOGITS
     possibil
    0.09
     conduct
    0.08
    ивая
    0.08
     pencil
    0.07
     assistance
    0.07
    дый
    0.07
    мит
    0.07
     textiles
    0.07
     possibility
    0.07
    ็ด
    0.07
    Activations Density 0.002%

    No Known Activations