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. 44073
    Prev
    Next
    INDEX
    Explanations

    Formal notation

    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
     нашего
    -0.08
     package
    -0.07
     outer
    -0.07
     ಎರಡ
    -0.07
     нашу
    -0.07
     VG
    -0.07
     сахар
    -0.07
     biops
    -0.07
    igue
    -0.07
     für
    -0.07
    POSITIVE LOGITS
     deveria
    0.09
     Idol
    0.09
     Mast
    0.08
    stätten
    0.08
     Having
    0.08
     Baj
    0.08
    应该
    0.08
     eid
    0.08
     devastation
    0.08
    ☆☆
    0.08
    Activations Density 0.000%

    No Known Activations