© 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. 111403
    Prev
    Next
    INDEX
    Explanations

    internal

    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
     ous
    -0.09
     timely
    -0.08
     eagerly
    -0.08
    _atom
    -0.07
     out
    -0.07
     danh
    -0.07
     bean
    -0.07
     sas
    -0.07
     serm
    -0.07
     Atom
    -0.07
    POSITIVE LOGITS
    sections
    0.08
    _MAX
    0.08
    AW
    0.08
    և
    0.08
    isans
    0.08
    lining
    0.08
    enum
    0.07
    story
    0.07
    Aw
    0.07
    станов
    0.07
    Activations Density 0.001%

    No Known Activations