© 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 EvalsExportsAPI 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. 21230
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     and
    -0.11
     અને
    -0.09
     niet
    -0.09
     ಮತ್ತು
    -0.09
     và
    -0.09
     и
    -0.08
     आणि
    -0.08
     aqueles
    -0.08
     aquelas
    -0.08
     ireo
    -0.08
    POSITIVE LOGITS
    २०
    0.09
    २
    0.09
    ၂၀
    0.08
    .medium
    0.08
    =v
    0.08
    =${
    0.08
    <|end|>
    0.08
     అత్య
    0.08
    २०७
    0.08
    ३
    0.08
    Activations Density 0.007%

    No Known Activations