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. 59251
    Prev
    Next
    INDEX
    Explanations

    dynamic

    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
     Quebec
    -0.09
     America
    -0.09
     Lenn
    -0.08
     quell
    -0.08
    ugit
    -0.08
     stave
    -0.08
     Spielberg
    -0.08
     abundant
    -0.08
     Kris
    -0.08
     vlas
    -0.08
    POSITIVE LOGITS
    Dynamic
    0.10
    .live
    0.08
     Dynamic
    0.08
     exploits
    0.08
    Plain
    0.08
    Injection
    0.08
    ライブ
    0.07
    -assisted
    0.07
    Domain
    0.07
    Anti
    0.07
    Activations Density 0.001%

    No Known Activations