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. 15-RESID-POST-AA
    6. 19000
    Prev
    Next
    INDEX
    Explanations

    \

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     particular
    -0.11
     ಅದು
    -0.10
     nếu
    -0.10
     ಅವರು
    -0.09
     benodigde
    -0.09
     ವಿಶೇಷ
    -0.09
     özellikle
    -0.09
     ಇದು
    -0.09
     частности
    -0.09
    ímp
    -0.09
    POSITIVE LOGITS
    ed
    0.09
    ized
    0.09
    ে
    0.07
    -z
    0.07
    -derived
    0.07
     "
    0.07
    ি
    0.07
    ly
    0.07
    -level
    0.07
    -only
    0.07
    Activations Density 0.097%

    No Known Activations