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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69009
    Prev
    Next
    INDEX
    Explanations

    displacement

    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
     Klub
    -0.08
    	Load
    -0.08
     bee
    -0.08
    -0.08
     evol
    -0.08
    cepts
    -0.07
    _load
    -0.07
     deque
    -0.07
     λεπ
    -0.07
     erkennt
    -0.07
    POSITIVE LOGITS
     due
    0.08
     aufgrund
    0.08
     vested
    0.08
     �
    0.08
     CER
    0.08
     devido
    0.08
     formen
    0.07
     pension
    0.07
     камп
    0.07
     Gordon
    0.07
    Activations Density 0.009%
    No Known Activations