© 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. 54642
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     geht
    -0.08
     warn
    -0.07
    一种
    -0.07
     ngadto
    -0.07
     composer
    -0.07
     uno
    -0.07
    houding
    -0.07
    anking
    -0.07
     XXL
    -0.07
     ਹੀ
    -0.07
    POSITIVE LOGITS
     Flaming
    0.09
    icator
    0.08
     inc
    0.07
    △
    0.07
     establishment
    0.07
     Fig
    0.07
    'inc
    0.07
     tém
    0.07
     маш
    0.07
     excl
    0.07
    Activations Density 0.025%

    No Known Activations