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. 65191
    Prev
    Next
    INDEX
    Explanations

    Cytochromes

    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
    Locator
    -0.08
     allowances
    -0.08
    Aj
    -0.08
    idente
    -0.08
    idem
    -0.08
    ಿವ
    -0.08
    George
    -0.08
    iraa
    -0.07
    itatem
    -0.07
     Sonoma
    -0.07
    POSITIVE LOGITS
     prolet
    0.09
     breeder
    0.08
     सं
    0.08
     Clas
    0.07
     kleuren
    0.07
     배우
    0.07
     Falls
    0.07
     সিন
    0.07
     écl
    0.07
     الاص
    0.07
    Activations Density 0.001%

    No Known Activations