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. 60704
    Prev
    Next
    INDEX
    Explanations

    number theory

    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
    -0.08
     hs
    -0.07
    써
    -0.07
     viruses
    -0.07
     recension
    -0.07
     onboarding
    -0.07
    üm
    -0.07
    uite
    -0.07
     cien
    -0.07
     EVENTS
    -0.07
    POSITIVE LOGITS
    _bits
    0.10
    Bits
    0.09
     bits
    0.08
     Bits
    0.08
    .bits
    0.08
     tiled
    0.08
     components
    0.08
    ارى
    0.08
     dadi
    0.08
    .bytes
    0.08
    Activations Density 0.007%

    No Known Activations