© 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. 69915
    Prev
    Next
    INDEX
    Explanations

    about

    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
     transf
    -0.09
    详
    -0.07
     faz
    -0.07
     noir
    -0.07
     ض
    -0.07
    <=
    -0.07
    Rol
    -0.07
    Dif
    -0.07
     المرت
    -0.07
     straw
    -0.07
    POSITIVE LOGITS
     việc
    0.08
     Panther
    0.08
     thriving
    0.08
    omit
    0.07
     wound
    0.07
     Jack
    0.07
     Joe
    0.07
     Elizabeth
    0.07
     fuels
    0.07
     equil
    0.07
    Activations Density 0.126%

    No Known Activations