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. 113813
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
     ताकि
    -0.10
     Tear
    -0.08
     যাতে
    -0.08
    เพื่อ
    -0.08
     ক্ষ
    -0.08
     Deinen
    -0.07
     чтобы
    -0.07
     כדי
    -0.07
     מנת
    -0.07
     เพื่อ
    -0.07
    POSITIVE LOGITS
    ithiol
    0.08
     revamped
    0.08
    unicip
    0.08
     supplemented
    0.08
    нив
    0.08
     dibanding
    0.08
     multicultural
    0.08
     vask
    0.08
     moder
    0.08
     overhaul
    0.08
    Activations Density 0.068%

    No Known Activations