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. 7-RESID-POST-AA
    6. 131038
    Prev
    Next
    INDEX
    Explanations

    18

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    িস
    -0.08
     шту
    -0.08
    NU
    -0.08
    "B
    -0.07
    anyol
    -0.07
     purposeful
    -0.07
    "url
    -0.07
    做到
    -0.07
    url
    -0.07
    						 
    -0.07
    POSITIVE LOGITS
     Robo
    0.09
     cherished
    0.08
     anxious
    0.08
     ansiedade
    0.08
    🏼
    0.08
    cela
    0.08
     ansiedad
    0.08
     cortisol
    0.08
     anxiety
    0.08
     Anxiety
    0.07
    Activations Density 0.016%

    No Known Activations