© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49969
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hynny
    -0.09
     proporcionando
    -0.08
    so
    -0.08
    ?,?,
    -0.08
     aiding
    -0.08
     offrant
    -0.08
     იმისა
    -0.08
     immersion
    -0.08
     hope
    -0.08
     permitindo
    -0.07
    POSITIVE LOGITS
     signifie
    0.18
     specifically
    0.18
     means
    0.18
     означает
    0.18
     significa
    0.17
    意味着
    0.17
     betekent
    0.17
     tähendab
    0.17
     znači
    0.17
     bedeutet
    0.16
    Activations Density 0.084%

    No Known Activations