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. 102891
    Prev
    Next
    INDEX
    Explanations

    area

    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
     വെ
    -0.08
     Mach
    -0.08
    Mon
    -0.08
    _arr
    -0.08
    -0.07
    .tv
    -0.07
    -0.07
     sever
    -0.07
    Nar
    -0.07
    实际上
    -0.07
    POSITIVE LOGITS
    thers
    0.08
     qualifying
    0.08
     九
    0.08
     aprovechar
    0.07
     Molly
    0.07
     daño
    0.07
     希
    0.07
     daños
    0.07
    面积
    0.07
     ضلع
    0.07
    Activations Density 0.028%

    No Known Activations