© 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. 11-RESID-POST-AA
    6. 25173
    Prev
    Next
    INDEX
    Explanations

    anticipate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resigned
    -0.08
     Poison
    -0.08
     Resolver
    -0.07
    =");↵
    -0.07
    .mods
    -0.07
    sound
    -0.07
     ");↵
    -0.07
     Resp
    -0.07
     SOUND
    -0.07
     "))
    -0.07
    POSITIVE LOGITS
     necessidades
    0.09
    udience
    0.09
     vervolg
    0.09
     households
    0.08
     سين
    0.08
    हु
    0.08
    حتاج
    0.08
    Funding
    0.08
     هو
    0.07
     സാഹചര
    0.07
    Activations Density 0.023%

    No Known Activations