Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53070
    Prev
    Next
    INDEX
    Explanations

    programming and foreign languages

    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
     whale
    -0.08
    ITAL
    -0.08
     Gong
    -0.07
     nội
    -0.07
     Racer
    -0.07
     vaig
    -0.07
     ফুল
    -0.07
    ennial
    -0.07
     �
    -0.07
     vão
    -0.07
    POSITIVE LOGITS
     disso
    0.16
     이에
    0.15
     thereof
    0.15
     이를
    0.15
    对此
    0.15
    其中
    0.14
     therein
    0.14
     thereto
    0.14
     hiervan
    0.14
     لذلك
    0.14
    Activations Density 0.596%

    No Known Activations