© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110380
    Prev
    Next
    INDEX
    Explanations

    prime 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
     dye
    -0.08
    overwrite
    -0.08
    _damage
    -0.08
     dyes
    -0.08
    ựa
    -0.08
     послед
    -0.08
    _assets
    -0.08
    _GUI
    -0.08
    水平
    -0.08
     имущества
    -0.08
    POSITIVE LOGITS
     primes
    0.10
     sieve
    0.10
     cor
    0.10
     infinite
    0.08
     jihad
    0.08
     motiv
    0.08
     sayı
    0.08
     Infinite
    0.08
     prostat
    0.08
     giv
    0.08
    Activations Density 0.021%

    No Known Activations