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. 113866
    Prev
    Next
    INDEX
    Explanations

    722

    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
    icais
    -0.09
     நடந்த
    -0.08
    vorming
    -0.08
    RESULT
    -0.08
     Staat
    -0.08
     CONST
    -0.08
     Persönlichkeit
    -0.08
     형태
    -0.08
    �다
    -0.08
     ঘট
    -0.08
    POSITIVE LOGITS
     ajili
    0.11
     поч
    0.08
     для
    0.08
     dành
    0.08
    _for
    0.08
     purposes
    0.08
     purpose
    0.08
    Each
    0.08
    τί
    0.08
     fún
    0.08
    Activations Density 0.060%

    No Known Activations