© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 16568
    Prev
    Next
    INDEX
    Explanations

    Placeholders or typos

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .More
    -0.08
    .Blue
    -0.08
     importantly
    -0.08
     fő
    -0.08
     plenty
    -0.08
     гораздо
    -0.08
     әс
    -0.08
    álaga
    -0.07
    irá
    -0.07
     wesentlich
    -0.07
    POSITIVE LOGITS
     mistakenly
    0.08
    .placeholder
    0.08
     (?)
    0.08
     entendido
    0.08
     placeholder
    0.08
    placeholder
    0.08
    ???
    0.08
    Placeholder
    0.08
     nonexistent
    0.08
     Placeholder
    0.08
    Activations Density 0.022%

    No Known Activations