© 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 EvalsExportsinterp-engineNEWAPI 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. 110574
    Prev
    Next
    INDEX
    Explanations

    energy

    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
     idir
    -0.09
     definitions
    -0.08
     €/
    -0.08
     wchar
    -0.08
     GER
    -0.08
    definitions
    -0.08
     widgets
    -0.08
     жид
    -0.07
    drivers
    -0.07
     chemo
    -0.07
    POSITIVE LOGITS
    مالك
    0.08
    Bil
    0.08
    .cm
    0.08
     لديها
    0.08
    Scheduled
    0.08
     bil
    0.08
    _sat
    0.08
    -owned
    0.08
    _sched
    0.08
     terlebih
    0.07
    Activations Density 0.004%

    No Known Activations