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. 106161
    Prev
    Next
    INDEX
    Explanations

    to

    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
    (GPIO
    -0.08
     Parmi
    -0.08
    (GLFW
    -0.08
    (verbose
    -0.08
    angana
    -0.08
    (has
    -0.07
     matériels
    -0.07
    主义
    -0.07
    先进
    -0.07
     habit
    -0.07
    POSITIVE LOGITS
     izv
    0.09
    atoria
    0.09
    వ్య
    0.08
    _SER
    0.08
    -exclusive
    0.08
     Sao
    0.08
     over
    0.08
     Juli
    0.08
    005
    0.07
    Exclusive
    0.07
    Activations Density 0.025%

    No Known Activations