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. 23-RESID-POST-AA
    6. 98043
    Prev
    Next
    INDEX
    Explanations

    s

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pá
    -0.08
     Worc
    -0.08
     üz
    -0.08
     rá
    -0.08
     eject
    -0.07
     dizziness
    -0.07
     arte
    -0.07
     informed
    -0.07
    Reuse
    -0.07
    502
    -0.07
    POSITIVE LOGITS
    arga
    0.08
    olwa
    0.08
    ద
    0.08
     americans
    0.08
     amici
    0.08
    uma
    0.07
    ophones
    0.07
    넘
    0.07
     counters
    0.07
     norske
    0.07
    Activations Density 0.000%

    No Known Activations