© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96965
    Prev
    Next
    INDEX
    Explanations

    舒 and 调

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    informatics
    -0.09
    тем
    -0.07
     patri
    -0.07
     wc
    -0.07
     ಹಾಕ
    -0.07
     zasad
    -0.07
    itsch
    -0.07
    GRAM
    -0.07
    informat
    -0.07
     ugly
    -0.07
    POSITIVE LOGITS
    适
    0.16
     расслаб
    0.15
    適
    0.14
     ontsp
    0.13
     отдых
    0.12
     ontspannen
    0.12
    舒
    0.12
    舒服
    0.11
     respite
    0.11
    乐城
    0.11
    Activations Density 0.008%

    No Known Activations