© 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. 3-RESID-POST-AA
    11. 3165
    Prev
    Next
    INDEX
    Explanations

    space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bons
    -0.08
    PAT
    -0.08
    etras
    -0.08
    射
    -0.08
    ेव
    -0.08
    �
    -0.07
    辛
    -0.07
     cess
    -0.07
    BS
    -0.07
     الاتصال
    -0.07
    POSITIVE LOGITS
     kö
    0.09
     noticeable
    0.07
     REM
    0.07
     sagt
    0.07
     perif
    0.07
     Hubbard
    0.07
     FORE
    0.07
     UK
    0.07
     pendiente
    0.07
     ξε
    0.07
    Activations Density 0.003%

    No Known Activations