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. 77278
    Prev
    Next
    INDEX
    Explanations

    Bioshock

    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
     Torque
    -0.08
    �
    -0.08
    halts
    -0.08
     الله
    -0.08
    navbar
    -0.08
     Echt
    -0.08
    님
    -0.07
    GPU
    -0.07
     пап
    -0.07
     Centre
    -0.07
    POSITIVE LOGITS
    luc
    0.10
     memoir
    0.09
     stocked
    0.08
     encyclopedia
    0.08
     morality
    0.08
     minted
    0.08
     Elton
    0.08
    ೀಚ
    0.08
     tomo
    0.08
     biometric
    0.07
    Activations Density 0.001%

    No Known Activations