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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102811
    Prev
    Next
    INDEX
    Explanations

    types

    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
     কর্মক
    -0.10
     Handlung
    -0.09
     faaliyet
    -0.09
    依法
    -0.08
     కార్యక
    -0.08
     fundament
    -0.08
    -0.08
     Tätigkeit
    -0.08
     당시
    -0.08
     tegev
    -0.08
    POSITIVE LOGITS
     beginners
    0.13
     erhältlich
    0.12
     beginner
    0.12
     verkrijgbaar
    0.12
     empfe
    0.11
     варианты
    0.11
     manufacturers
    0.11
    bieter
    0.11
     خيارات
    0.11
     opciones
    0.10
    Activations Density 0.149%

    No Known Activations