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. 54162
    Prev
    Next
    INDEX
    Explanations

    mouse

    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
    ên
    -0.09
     yaşayan
    -0.08
     beg
    -0.07
     ಸಂದರ್ಭದಲ್ಲಿ
    -0.07
     desirable
    -0.07
    Su
    -0.07
    �
    -0.07
    ierungs
    -0.07
     ಸ
    -0.07
     newborn
    -0.07
    POSITIVE LOGITS
    ее
    0.08
     क्लिक
    0.08
     Frederick
    0.08
     Bor
    0.08
    ellas
    0.08
    0.08
     ход
    0.07
     slick
    0.07
    759
    0.07
     Storm
    0.07
    Activations Density 0.002%

    No Known Activations