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. 67844
    Prev
    Next
    INDEX
    Explanations

    Dragon Ball

    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
     Subsid
    -0.08
    财政
    -0.08
    уман
    -0.08
     Town
    -0.08
    GPS
    -0.08
     efecto
    -0.07
     차량
    -0.07
    资金
    -0.07
     GPS
    -0.07
     dwell
    -0.07
    POSITIVE LOGITS
     श्रेष्ठ
    0.10
     शक्त
    0.10
    实力
    0.09
     overpower
    0.09
     pouvoirs
    0.09
     üstün
    0.09
     duel
    0.09
     chakra
    0.08
     wali
    0.08
     powerhouse
    0.08
    Activations Density 0.050%

    No Known Activations