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. 44049
    Prev
    Next
    INDEX
    Explanations

    4

    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
    &e
    -0.09
     Linux
    -0.08
     mpg
    -0.08
     linux
    -0.07
     Moodle
    -0.07
     Maestro
    -0.07
     checkpoint
    -0.07
     Chrome
    -0.07
     Amazon
    -0.07
     مث
    -0.07
    POSITIVE LOGITS
     lainnya
    0.08
     saiu
    0.08
     unabh
    0.08
     αποκ
    0.08
     сделали
    0.08
     równie
    0.08
     nhau
    0.07
     dédi
    0.07
     lập
    0.07
    osphere
    0.07
    Activations Density 0.055%

    No Known Activations