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. 58848
    Prev
    Next
    INDEX
    Explanations

    period

    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
     pun
    -0.08
     carbohydrate
    -0.07
    Essential
    -0.07
     crude
    -0.07
    춤
    -0.07
     overseas
    -0.07
    oglio
    -0.07
    ölker
    -0.07
    ind
    -0.07
    cement
    -0.07
    POSITIVE LOGITS
     máy
    0.08
    139
    0.08
     supremacy
    0.08
     bulb
    0.07
     개인
    0.07
     HDMI
    0.07
     reckon
    0.07
    ענע
    0.07
    localhost
    0.07
     રહી
    0.07
    Activations Density 0.002%

    No Known Activations