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. 106178
    Prev
    Next
    INDEX
    Explanations

    expression

    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
     Leib
    -0.08
     Le
    -0.07
     Princess
    -0.07
     fra
    -0.07
    Provision
    -0.07
    -Le
    -0.07
    lau
    -0.07
    ilde
    -0.07
    omo
    -0.07
    EXPORT
    -0.06
    POSITIVE LOGITS
    睛
    0.11
    脸
    0.09
    pector
    0.09
     Facial
    0.08
    ję
    0.08
     göz
    0.08
     سأ
    0.08
     wash
    0.08
    制作
    0.08
    uate
    0.08
    Activations Density 0.007%

    No Known Activations