Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88058
    Prev
    Next
    INDEX
    Explanations

    glass

    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
     gam
    -0.08
    .loc
    -0.08
     academ
    -0.07
     Kost
    -0.07
     rescu
    -0.07
     rescue
    -0.07
     screw
    -0.07
     resc
    -0.07
     Royals
    -0.07
     Paw
    -0.07
    POSITIVE LOGITS
     topped
    0.08
     vapor
    0.08
     pointed
    0.08
     Vap
    0.07
    ware
    0.07
     vap
    0.07
    blower
    0.07
    描
    0.07
     Stad
    0.07
     cases
    0.07
    Activations Density 0.012%

    No Known Activations