© 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. 13429
    Prev
    Next
    INDEX
    Explanations

    hovered

    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
    147
    -0.09
    -0.08
    hu
    -0.08
     Giving
    -0.08
     behold
    -0.08
    rá
    -0.08
    Testimonials
    -0.07
    রের
    -0.07
    Ints
    -0.07
     dispro
    -0.07
    POSITIVE LOGITS
    boarding
    0.08
    kv
    0.07
    课
    0.07
    _magic
    0.07
     прос
    0.07
     Tropical
    0.07
     pros
    0.07
    bild
    0.07
    wiki
    0.07
     princip
    0.07
    Activations Density 0.001%
    No Known Activations