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. 45581
    Prev
    Next
    INDEX
    Explanations

    Apologies and congratulations

    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
    циони
    -0.07
     debated
    -0.07
     calibr
    -0.07
     equilibr
    -0.07
     tính
    -0.07
    Бу
    -0.07
    (?)
    -0.07
     cadáver
    -0.07
    ()[
    -0.07
     lessons
    -0.07
    POSITIVE LOGITS
     br
    0.08
    ail
    0.08
     Tide
    0.08
     elementum
    0.07
    이며
    0.07
    meen
    0.07
     باللغة
    0.07
     aner
    0.07
     wholehearted
    0.07
     wsz
    0.07
    Activations Density 0.023%

    No Known Activations