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. 12197
    Prev
    Next
    INDEX
    Explanations

    CFD

    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
     কর্ত
    -0.08
     mana
    -0.08
     Eure
    -0.08
    adeed
    -0.07
    andon
    -0.07
    .pl
    -0.07
    ിക്ക
    -0.07
     خو
    -0.07
     אפילו
    -0.07
     center
    -0.07
    POSITIVE LOGITS
     anbieten
    0.10
    (item
    0.10
     ofrecemos
    0.10
     제공
    0.09
    )item
    0.09
    :item
    0.09
     offered
    0.09
     제공합니다
    0.09
     aanbieden
    0.08
     만들
    0.08
    Activations Density 0.001%

    No Known Activations