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. 30555
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
    ldon
    -0.09
    nome
    -0.08
    night
    -0.08
     Fighting
    -0.08
    enced
    -0.08
    avna
    -0.08
    encing
    -0.07
    elfth
    -0.07
    znam
    -0.07
    kampf
    -0.07
    POSITIVE LOGITS
     suf
    0.08
     transmit
    0.08
     anges
    0.08
     iv
    0.07
     invari
    0.07
    ்ட
    0.07
     تص
    0.07
     opr
    0.07
     grow
    0.07
    عا
    0.07
    Activations Density 0.012%

    No Known Activations