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. 49837
    Prev
    Next
    INDEX
    Explanations

    mathematical properties

    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
     Emily
    -0.07
     Pregnancy
    -0.07
    -0.07
     unstable
    -0.07
     pregnancy
    -0.07
     Micha
    -0.07
     account
    -0.07
     minna
    -0.07
     Ministry
    -0.07
     Stella
    -0.07
    POSITIVE LOGITS
    .payload
    0.08
    ייז
    0.08
     Trout
    0.08
    .abspath
    0.08
    маган
    0.08
     задум
    0.08
    uating
    0.08
     мужчина
    0.08
    ใหญ่
    0.08
    ụụ
    0.08
    Activations Density 0.133%

    No Known Activations