Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19059
    Prev
    Next
    INDEX
    Explanations

    stabilize

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iskust
    -0.07
     neka
    -0.07
     municipalities
    -0.07
    巨
    -0.07
    浪
    -0.07
     overflow
    -0.07
    fahrung
    -0.07
    িছ
    -0.07
     asynchronously
    -0.07
     darüber
    -0.07
    POSITIVE LOGITS
    稳定
    0.12
     стабиль
    0.11
     안정
    0.11
     стаб
    0.10
     സ്ഥിര
    0.10
     stabilize
    0.10
     estabil
    0.10
     satisfactory
    0.09
     stabilization
    0.09
     Stabil
    0.09
    Activations Density 0.003%

    No Known Activations