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. 7-RESID-POST-AA
    6. 131046
    Prev
    Next
    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     joystick
    -0.08
     MRT
    -0.07
    ד
    -0.07
     manifold
    -0.07
     decom
    -0.07
     сол
    -0.07
     geringer
    -0.07
    ולה
    -0.07
    収
    -0.07
     demeanor
    -0.07
    POSITIVE LOGITS
     Pall
    0.08
    ptest
    0.08
    assion
    0.08
     Orden
    0.08
     witnessing
    0.08
     Poli
    0.08
     Einzahlung
    0.08
     Aw
    0.07
     hozzá
    0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.07
    Activations Density 0.005%

    No Known Activations