© 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. 99456
    Prev
    Next
    INDEX
    Explanations

    battle

    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
     Mitchell
    -0.08
    mir
    -0.08
     �
    -0.08
     сус
    -0.07
     svært
    -0.07
     डी
    -0.07
    -ज
    -0.07
    mein
    -0.07
     વિશ્વ
    -0.07
     Tav
    -0.07
    POSITIVE LOGITS
     chore
    0.08
    地点
    0.08
     случа
    0.08
     chau
    0.08
     Budapest
    0.08
    -winning
    0.08
     sonrası
    0.07
    لل
    0.07
     ا
    0.07
     royale
    0.07
    Activations Density 0.027%

    No Known Activations