© 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. 91835
    Prev
    Next
    INDEX
    Explanations

    of

    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
    >(↵
    -0.08
     මේ
    -0.08
    とか
    -0.08
     malpractice
    -0.08
     fus
    -0.07
     publish
    -0.07
     stagnant
    -0.07
    يسي
    -0.07
     أحدث
    -0.07
    ตาม
    -0.07
    POSITIVE LOGITS
    -là
    0.20
     pomo
    0.08
    বার
    0.08
    看来
    0.08
     �
    0.08
     chắc
    0.07
    -conscious
    0.07
     nhằm
    0.07
    ,len
    0.07
     determinant
    0.07
    Activations Density 0.488%

    No Known Activations