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. 106225
    Prev
    Next
    INDEX
    Explanations

    SE

    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
    九
    -0.09
    )("
    -0.09
     Copp
    -0.08
     nanti
    -0.08
    未知
    -0.08
    棋
    -0.08
    ڑی
    -0.08
     herd
    -0.08
    COP
    -0.08
     lokacin
    -0.08
    POSITIVE LOGITS
    brevi
    0.07
     literally
    0.07
    -quality
    0.07
    @email
    0.07
     Caes
    0.07
     Cheap
    0.07
     Junior
    0.07
    gue
    0.07
    literal
    0.07
     эконом
    0.07
    Activations Density 0.002%

    No Known Activations