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. 11846
    Prev
    Next
    INDEX
    Explanations

    ce

    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
    �
    -0.09
     enrollment
    -0.08
    國
    -0.08
     telescope
    -0.07
    (vertical
    -0.07
    (IS
    -0.07
    Jap
    -0.07
    Enroll
    -0.07
     gok
    -0.07
     bên
    -0.07
    POSITIVE LOGITS
     الدم
    0.08
     شعار
    0.08
     Holder
    0.08
    achos
    0.08
     sentido
    0.08
    jud
    0.08
     Vision
    0.08
    endra
    0.08
    ensas
    0.08
     Cream
    0.07
    Activations Density 0.000%

    No Known Activations