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. 11724
    Prev
    Next
    INDEX
    Explanations

    theory

    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
     verschijnt
    -0.08
     πρόγραμμα
    -0.08
     برامج
    -0.08
     פונ
    -0.08
     برنامج
    -0.08
     العد
    -0.07
     streamer
    -0.07
     barrage
    -0.07
     Riders
    -0.07
    .scene
    -0.07
    POSITIVE LOGITS
     പോല
    0.08
     applied
    0.08
    -inspired
    0.08
    (Create
    0.07
     principles
    0.07
    Nesse
    0.07
    ®
    0.07
    mic
    0.07
     profit
    0.07
    ारे
    0.07
    Activations Density 0.011%

    No Known Activations