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. 11858
    Prev
    Next
    INDEX
    Explanations

    Molecular cloning

    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
     volupt
    -0.08
    िब
    -0.08
     fighter
    -0.08
    ajr
    -0.08
    疲
    -0.08
     दर्द
    -0.08
    Expenses
    -0.08
     Expenses
    -0.08
    Departure
    -0.08
     Meditation
    -0.08
    POSITIVE LOGITS
     cloning
    0.10
     GFP
    0.10
     clones
    0.09
    (insert
    0.09
     accession
    0.09
     inserting
    0.09
     recombinant
    0.09
     Insert
    0.09
    	insert
    0.09
     растений
    0.09
    Activations Density 0.012%

    No Known Activations