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

    Neuronpedia

    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. 99416
    Prev
    Next
    INDEX
    Explanations

    to

    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
    孤
    -0.08
     תש
    -0.08
     slump
    -0.08
    singleton
    -0.07
    -country
    -0.07
    listed
    -0.07
    annual
    -0.07
    weep
    -0.07
     auk
    -0.07
    -reviewed
    -0.07
    POSITIVE LOGITS
     rozpoc
    0.10
     stopwatch
    0.09
     løpet
    0.09
    多久
    0.09
     Ly
    0.09
     elapsed
    0.09
     начала
    0.09
     dauern
    0.09
    ाक्ष
    0.09
     inicio
    0.09
    Activations Density 0.015%

    No Known Activations