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. 87993
    Prev
    Next
    INDEX
    Explanations

    circles

    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
    遊
    -0.08
     partic
    -0.07
    Python
    -0.07
     verste
    -0.07
     creatures
    -0.07
     oubl
    -0.07
     hortic
    -0.07
    ,'
    -0.07
    redis
    -0.07
     insects
    -0.07
    POSITIVE LOGITS
    (vc
    0.09
     pvc
    0.09
     έχουν
    0.09
     SNAP
    0.09
    طط
    0.08
     Luca
    0.08
    ущий
    0.08
    .Setter
    0.08
     PAC
    0.08
     المختلفة
    0.08
    Activations Density 0.016%

    No Known Activations