© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103461
    Prev
    Next
    INDEX
    Explanations

    make

    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
     a
    -0.11
     an
    -0.11
     additional
    -0.09
     one
    -0.09
    provement
    -0.09
     several
    -0.08
     something
    -0.08
     משהו
    -0.08
     extra
    -0.08
     many
    -0.08
    POSITIVE LOGITS
     Sure
    0.09
    川県
    0.08
    .synthetic
    0.08
    PRICE
    0.08
    .Country
    0.08
     ಕೋ
    0.08
    ைப்
    0.08
    ензи
    0.08
    텐
    0.08
    .toolbox
    0.08
    Activations Density 0.036%

    No Known Activations