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. 30502
    Prev
    Next
    INDEX
    Explanations

    :

    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
    ñ
    -0.08
    ור
    -0.08
     znam
    -0.08
     turist
    -0.08
     aspek
    -0.07
     Erit
    -0.07
    Steph
    -0.07
     quel
    -0.07
     aspet
    -0.07
     נח
    -0.07
    POSITIVE LOGITS
     наст
    0.08
     brightness
    0.07
     ول
    0.07
     الاعت
    0.07
     falsely
    0.07
     guitar
    0.07
     asumir
    0.07
     мя
    0.07
     fluorescence
    0.07
    rast
    0.07
    Activations Density 0.094%

    No Known Activations