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. 49254
    Prev
    Next
    INDEX
    Explanations

    CLIP and language models

    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
     Medina
    -0.09
     Municipal
    -0.09
     marl
    -0.08
     municipality
    -0.08
     khai
    -0.08
     municipal
    -0.08
     Süd
    -0.08
     barber
    -0.08
     Salary
    -0.08
    işli
    -0.08
    POSITIVE LOGITS
     cognition
    0.09
    .Image
    0.09
    _attention
    0.09
     coupling
    0.09
    _image
    0.08
     semantic
    0.08
     halluc
    0.08
    ಚಿತ್ರ
    0.08
    Image
    0.08
    =image
    0.08
    Activations Density 0.006%

    No Known Activations