Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 53938
    Prev
    Next
    INDEX
    Explanations

    describing individuals

    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
     fortunes
    -0.09
     Nev
    -0.08
     myriad
    -0.08
    (credentials
    -0.08
     alike
    -0.08
     suprem
    -0.08
     expelled
    -0.07
    ост
    -0.07
     estaduais
    -0.07
    —that
    -0.07
    POSITIVE LOGITS
     없음
    0.10
    none
    0.10
     none
    0.10
    .None
    0.09
    .none
    0.08
    且
    0.08
    _none
    0.08
    ಿಸಲಾಗಿದೆ
    0.08
    ucune
    0.08
     yes
    0.08
    Activations Density 0.353%

    No Known Activations