© 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. 44305
    Prev
    Next
    INDEX
    Explanations

    易

    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
    før
    -0.09
     gerek
    -0.08
     Evo
    -0.08
     surplus
    -0.07
     Interviews
    -0.07
     Tok
    -0.07
    tn
    -0.07
     Ler
    -0.07
    odo
    -0.07
    gett
    -0.07
    POSITIVE LOGITS
     dàng
    0.09
    於
    0.08
    々
    0.08
     Autob
    0.07
    ที่จะ
    0.07
     transcend
    0.07
     বিষ
    0.07
    eway
    0.07
    বার
    0.07
     degrade
    0.07
    Activations Density 0.005%

    No Known Activations