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. 113809
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    آلة
    -0.09
     هم
    -0.08
    ാക
    -0.08
    -0.08
     specifically
    -0.08
     Jake
    -0.08
    actory
    -0.08
    ജ
    -0.08
     uninter
    -0.08
    ैक
    -0.07
    POSITIVE LOGITS
    TZID
    0.08
    Icons
    0.08
    Password
    0.08
    Accessibility
    0.08
     tissues
    0.08
    IBE
    0.08
    Passwords
    0.08
    Username
    0.07
    Sounds
    0.07
    icons
    0.07
    Activations Density 0.001%

    No Known Activations