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. 75939
    Prev
    Next
    INDEX
    Explanations

    indeed

    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
    宁县
    -0.07
    -built
    -0.07
     helping
    -0.07
     '${
    -0.07
    SAR
    -0.07
     الن
    -0.07
    kiego
    -0.07
     Tark
    -0.07
    ddy
    -0.07
     Ver
    -0.07
    POSITIVE LOGITS
     arguably
    0.10
     logically
    0.08
     ambiguous
    0.08
     mathem
    0.08
     célébr
    0.08
     scientifically
    0.08
    Again
    0.08
     ambiguity
    0.08
     consciously
    0.08
     celebrated
    0.08
    Activations Density 0.104%

    No Known Activations