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. 43993
    Prev
    Next
    INDEX
    Explanations

    Set

    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
     demasiado
    -0.08
    -0.08
     Hag
    -0.08
     nummer
    -0.08
    Enough
    -0.07
     validity
    -0.07
     numer
    -0.07
     Sudan
    -0.07
     tolik
    -0.07
    &H
    -0.07
    POSITIVE LOGITS
     xác
    0.08
    iu
    0.08
     Нов
    0.08
     ಸೇರ
    0.08
     xpos
    0.07
     ನಾಲ
    0.07
    +'_
    0.07
     beings
    0.07
     규
    0.07
    잠
    0.07
    Activations Density 0.002%

    No Known Activations