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. 102776
    Prev
    Next
    INDEX
    Explanations

    exit

    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
     Davidson
    -0.08
     purchased
    -0.08
     avancer
    -0.08
     advanced
    -0.08
    875
    -0.07
     NCAA
    -0.07
     dissolved
    -0.07
     ಜಯ
    -0.07
    XP
    -0.07
     bought
    -0.07
    POSITIVE LOGITS
     Honest
    0.09
     permiso
    0.08
    itelisted
    0.08
     riz
    0.08
     honesty
    0.07
     Rendez
    0.07
     foco
    0.07
    ИТ
    0.07
     seh
    0.07
     Permissions
    0.07
    Activations Density 0.000%

    No Known Activations