© 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. 45669
    Prev
    Next
    INDEX
    Explanations

    with

    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
     Freight
    -0.08
    宣
    -0.08
     prag
    -0.07
     ולכן
    -0.07
     宣
    -0.07
     Atkins
    -0.07
     appropri
    -0.07
     बयान
    -0.07
     ibintu
    -0.07
     इस्तेमाल
    -0.07
    POSITIVE LOGITS
     Cum
    0.08
    zame
    0.08
    Cum
    0.08
    idores
    0.08
     PLA
    0.08
    .ta
    0.08
    (blank
    0.07
     practicing
    0.07
    'aka
    0.07
     стал
    0.07
    Activations Density 0.011%

    No Known Activations