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. 29895
    Prev
    Next
    INDEX
    Explanations

    technical and medical texts

    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
    aces
    -0.07
    Sequence
    -0.07
    佳
    -0.07
    �
    -0.07
    ennes
    -0.07
     prø
    -0.07
     sequence
    -0.07
    (tmp
    -0.07
     magically
    -0.07
     luyện
    -0.07
    POSITIVE LOGITS
    FULL
    0.09
     власть
    0.08
    .events
    0.08
    ్లీ
    0.07
     peso
    0.07
     эмо
    0.07
     historischen
    0.07
    mu
    0.07
    >N
    0.07
     peł
    0.07
    Activations Density 0.000%

    No Known Activations