© 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. 78217
    Prev
    Next
    INDEX
    Explanations

    chapter

    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
     STO
    -0.08
    _H
    -0.07
     -->↵
    -0.07
    krat
    -0.07
    -ST
    -0.07
     If
    -0.07
    是假
    -0.07
    _str
    -0.07
    _clear
    -0.07
     Check
    -0.07
    POSITIVE LOGITS
     chapter
    0.12
     этап
    0.11
     embarking
    0.10
     chapters
    0.10
     etapas
    0.10
     spannende
    0.10
     etapa
    0.10
     chapitre
    0.10
     boshl
    0.10
     embarked
    0.10
    Activations Density 0.042%

    No Known Activations