Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53012
    Prev
    Next
    INDEX
    Explanations

    Character descriptions

    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
     sín
    -0.09
     PATCH
    -0.09
     Gé
    -0.08
     بس
    -0.08
     credential
    -0.08
    CRM
    -0.08
     Patch
    -0.08
    Downloading
    -0.08
     CRM
    -0.07
     للبيع
    -0.07
    POSITIVE LOGITS
     annoying
    0.11
     awful
    0.10
     insane
    0.09
     havoc
    0.09
     annoyance
    0.09
     absurd
    0.09
     quirky
    0.09
     witty
    0.09
     परेशान
    0.08
     cynical
    0.08
    Activations Density 0.016%

    No Known Activations