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. 78658
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
     resumo
    -0.08
     retry
    -0.07
    �
    -0.07
    Resumo
    -0.07
    Retry
    -0.07
    (X
    -0.07
    Nun
    -0.07
    Replay
    -0.07
     repetir
    -0.07
     exclusive
    -0.07
    POSITIVE LOGITS
     variant
    0.09
     oğ
    0.09
    .variant
    0.09
     variants
    0.09
     variante
    0.09
    Variants
    0.08
    型号
    0.08
     Variant
    0.08
     kompleks
    0.08
     quello
    0.08
    Activations Density 0.346%

    No Known Activations