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. 43226
    Prev
    Next
    INDEX
    Explanations

    Mutexes and threading in code

    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
     grit
    -0.08
     usia
    -0.08
    _generator
    -0.08
    Generator
    -0.08
    .creator
    -0.07
     giveaway
    -0.07
    Presenter
    -0.07
    _stage
    -0.07
    Stage
    -0.07
    .Address
    -0.07
    POSITIVE LOGITS
     ഭരണ
    0.08
     تحرير
    0.08
     Consejo
    0.08
    -largest
    0.08
     Comité
    0.08
    กิจ
    0.08
     Lim
    0.08
     Adv
    0.07
     acte
    0.07
     Editing
    0.07
    Activations Density 0.002%

    No Known Activations