© 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. 18951
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    Aggregator
    -0.10
    Nigeria
    -0.10
    Boss
    -0.10
    _SERVICE
    -0.09
    _ONLY
    -0.09
    _Service
    -0.09
    _AF
    -0.09
    _IC
    -0.09
    قرير
    -0.09
    _Project
    -0.08
    POSITIVE LOGITS
    (?)
    0.10
    �
    0.10
    ×
    0.09
    ¢
    0.09
     ✅
    0.09
     dozen
    0.09
     (!)
    0.09
    µ
    0.09
     ✔
    0.09
    č
    0.09
    Activations Density 0.025%

    No Known Activations