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. 49227
    Prev
    Next
    INDEX
    Explanations

    trees

    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
     funds
    -0.08
     principle
    -0.07
     goodwill
    -0.07
     Euros
    -0.07
    	or
    -0.07
     asuntos
    -0.07
     
    -0.07
     деньги
    -0.07
    ರ್�
    -0.07
     sederhana
    -0.07
    POSITIVE LOGITS
     towering
    0.11
     engulf
    0.09
     richly
    0.09
     foliage
    0.09
     luxuri
    0.09
     vibrant
    0.08
    scape
    0.08
    .Tile
    0.08
     textura
    0.08
    遮
    0.08
    Activations Density 0.018%

    No Known Activations