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. 58317
    Prev
    Next
    INDEX
    Explanations

    hidden form fields

    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
    pron
    -0.09
     characterized
    -0.08
     celebrates
    -0.08
     admits
    -0.08
     થયો
    -0.08
     cavern
    -0.08
    Celebrate
    -0.08
     contraction
    -0.08
    Horn
    -0.08
     enjoys
    -0.08
    POSITIVE LOGITS
    csrf
    0.13
     csrf
    0.13
     nonce
    0.09
     ajax
    0.09
     tumour
    0.09
     AJAX
    0.09
    :hidden
    0.09
     enctype
    0.09
     hidden
    0.09
    _nonce
    0.09
    Activations Density 0.002%

    No Known Activations