© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 18653
    Prev
    Next
    INDEX
    Explanations

    say "exponentiation ending"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.09
     a
    -0.09
     '
    -0.08
     в
    -0.08
     these
    -0.08
     new
    -0.08
     v
    -0.08
     certain
    -0.07
     if
    -0.07
     R
    -0.07
    POSITIVE LOGITS
    なので
    0.11
    )::
    0.11
     nedenle
    0.11
    ,因此
    0.10
    )][
    0.10
     ולכן
    0.10
    )^
    0.10
    ,所以
    0.10
     હોવાથી
    0.09
     więc
    0.09
    Activations Density 0.048%

    No Known Activations