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. 112661
    Prev
    Next
    INDEX
    Explanations

    more

    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
     diary
    -0.08
    aking
    -0.07
     wearable
    -0.07
     DK
    -0.07
    -haired
    -0.07
    ening
    -0.07
     PX
    -0.07
     onboarding
    -0.07
    -0.07
    dryer
    -0.07
    POSITIVE LOGITS
    Calculate
    0.10
     calculate
    0.10
    .calculate
    0.09
     Calculate
    0.09
     riches
    0.09
     calcula
    0.08
     calcular
    0.08
     ટકા
    0.08
    от
    0.08
    จำนวน
    0.08
    Activations Density 0.006%

    No Known Activations