© 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. 78118
    Prev
    Next
    INDEX
    Explanations

    Dashes

    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
    fact
    -0.08
     hinge
    -0.08
    ummings
    -0.08
    mid
    -0.07
     factoring
    -0.07
     examining
    -0.07
    _IND
    -0.07
     vent
    -0.07
     confirm
    -0.07
    middleware
    -0.07
    POSITIVE LOGITS
     nelle
    0.09
    овыми
    0.08
     Bes
    0.08
     ihren
    0.08
     XK
    0.07
     denen
    0.07
    .patient
    0.07
     Guerre
    0.07
     João
    0.07
    кот
    0.07
    Activations Density 0.007%

    No Known Activations