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. 90241
    Prev
    Next
    INDEX
    Explanations

    country

    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
     Algebra
    -0.09
     forbidden
    -0.08
     habituales
    -0.08
     ALG
    -0.08
     venus
    -0.08
     alojamiento
    -0.08
     enem
    -0.07
     PCP
    -0.07
     correspondientes
    -0.07
     algebra
    -0.07
    POSITIVE LOGITS
     prosperity
    0.10
     સમાજ
    0.09
    奋斗
    0.09
     resilience
    0.09
     samenleving
    0.09
    사회
    0.09
     সমাজ
    0.08
     қоғам
    0.08
     발전
    0.08
     society
    0.08
    Activations Density 0.076%

    No Known Activations