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. 111585
    Prev
    Next
    INDEX
    Explanations

    break out

    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
    厚
    -0.08
    ろ
    -0.08
     Surgical
    -0.07
    ार्थ
    -0.07
     Pair
    -0.07
     gravity
    -0.07
    reserv
    -0.07
     Donation
    -0.07
    raulic
    -0.07
     Vacc
    -0.07
    POSITIVE LOGITS
     rire
    0.09
     laugh
    0.09
    笑
    0.08
     laughter
    0.08
    GN
    0.08
     shouting
    0.08
     khona
    0.08
     jaun
    0.08
     sonrisa
    0.08
     الصوت
    0.08
    Activations Density 0.009%

    No Known Activations