© 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. 30343
    Prev
    Next
    INDEX
    Explanations

    Synesthesia

    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
     suuren
    -0.08
     高
    -0.08
     ਗ
    -0.08
     wysok
    -0.07
     Hy
    -0.07
    ooq
    -0.07
    _H
    -0.07
    _HIGH
    -0.07
     chất
    -0.07
     Ant
    -0.07
    POSITIVE LOGITS
     uşa
    0.08
    unce
    0.08
     obl
    0.08
     infantil
    0.08
     bankers
    0.08
     TES
    0.08
     instituc
    0.08
     child's
    0.07
     evit
    0.07
    Ys
    0.07
    Activations Density 0.000%

    No Known Activations