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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 130274
    Prev
    Next
    INDEX
    Explanations

    a

    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
     also
    -0.08
    dec
    -0.08
     again
    -0.08
    -0.08
    atico
    -0.07
    +,
    -0.07
     fix
    -0.07
    deque
    -0.07
     enormous
    -0.07
     uses
    -0.07
    POSITIVE LOGITS
     داخلی
    0.09
     sesuai
    0.08
    анди
    0.08
    ристиан
    0.08
     عضو
    0.08
    veille
    0.08
     مكت
    0.08
    isek
    0.08
     pessoais
    0.08
     частью
    0.08
    Activations Density 0.002%

    No Known Activations