© 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. 11-RESID-POST-AA
    11. 54462
    Prev
    Next
    INDEX
    Explanations

    cooking instructions

    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
     Lib
    -0.08
     domestic
    -0.08
    .symmetric
    -0.08
    acom
    -0.08
    quet
    -0.08
     Pelosi
    -0.08
    ivr
    -0.07
    succ
    -0.07
     Ebola
    -0.07
    Phil
    -0.07
    POSITIVE LOGITS
     يم
    0.08
     ters
    0.07
     inode
    0.07
     يس
    0.07
     inception
    0.07
    ุม
    0.07
     policeman
    0.07
    устя
    0.07
    旁
    0.07
     طريق
    0.07
    Activations Density 0.049%

    No Known Activations