Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11890
    Prev
    Next
    INDEX
    Explanations

    segments "A", "2", or "0"

    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
     analyzing
    -0.08
    oration
    -0.08
    ضا
    -0.08
    adden
    -0.08
    estion
    -0.08
     тар
    -0.08
    -0.08
    cznych
    -0.08
    itized
    -0.07
     maîtrise
    -0.07
    POSITIVE LOGITS
     UART
    0.08
     BAC
    0.08
    UART
    0.08
     impost
    0.08
    afruit
    0.07
     Impro
    0.07
     Upr
    0.07
    宾
    0.07
     limpa
    0.07
     Spann
    0.07
    Activations Density 0.005%

    No Known Activations