© 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. 19-RESID-POST-AA
    11. 19167
    Prev
    Next
    INDEX
    Explanations

    say "every"

    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
    ssue
    -0.08
    žo
    -0.08
    _FACT
    -0.08
    Includes
    -0.08
    زمات
    -0.08
     różnych
    -0.07
    Different
    -0.07
    ouna
    -0.07
     المختلفة
    -0.07
     Breizh
    -0.07
    POSITIVE LOGITS
     every
    0.17
    every
    0.16
     Every
    0.14
     alternating
    0.12
    第
    0.12
     approximately
    0.12
     alternate
    0.12
    Every
    0.12
    alternate
    0.12
     第
    0.11
    Activations Density 0.012%

    No Known Activations