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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106330
    Prev
    Next
    INDEX
    Explanations

    relative

    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
    ရာ
    -0.10
    Fits
    -0.08
    akin
    -0.08
     Becker
    -0.08
    зя
    -0.08
     prév
    -0.07
    ojo
    -0.07
     qué
    -0.07
    /owl
    -0.07
     Wann
    -0.07
    POSITIVE LOGITS
     Hiz
    0.08
    /group
    0.08
     dynamics
    0.08
    usband
    0.08
     pend
    0.07
     Warfare
    0.07
     striker
    0.07
     movement
    0.07
     Mountain
    0.07
     Mechanics
    0.07
    Activations Density 0.005%

    No Known Activations