© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26592
    Prev
    Next
    INDEX
    Explanations

    large

    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
     перевод
    -0.08
     afili
    -0.08
     breeze
    -0.08
     wees
    -0.07
     troisième
    -0.07
    	async
    -0.07
    泉
    -0.07
     المت
    -0.07
    emps
    -0.07
    aham
    -0.07
    POSITIVE LOGITS
     overarching
    0.12
     enclosing
    0.11
     encompassing
    0.10
    ::__
    0.10
     larger
    0.09
    .Master
    0.09
    .parent
    0.09
    Parent
    0.09
     murals
    0.09
     outer
    0.08
    Activations Density 0.050%

    No Known Activations