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. 59573
    Prev
    Next
    INDEX
    Explanations

    Technology and societal evolution

    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
    Placeholder
    -0.07
    Percentage
    -0.07
    Handling
    -0.07
     מאוד
    -0.07
     consolation
    -0.07
    =false
    -0.07
    Referral
    -0.07
     šal
    -0.07
    DET
    -0.07
     &&
    -0.07
    POSITIVE LOGITS
    不断
    0.12
     continually
    0.11
     centuries
    0.11
     evolving
    0.10
     continual
    0.10
     발전
    0.10
     civilizations
    0.10
     history
    0.10
    history
    0.10
    तिहास
    0.10
    Activations Density 0.051%

    No Known Activations