© 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. 94459
    Prev
    Next
    INDEX
    Explanations

    afternoon

    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
    ilere
    -0.10
     stalk
    -0.07
     beno
    -0.07
     HOM
    -0.07
    bom
    -0.07
     vorz
    -0.07
    .Annotation
    -0.07
     ABO
    -0.07
    مثل
    -0.07
    _GR
    -0.07
    POSITIVE LOGITS
     afternoon
    0.10
    ternoons
    0.08
    用品
    0.08
     afternoons
    0.08
     Afternoon
    0.08
    ternoon
    0.08
     Sky
    0.07
     servants
    0.07
     sky
    0.07
     alp
    0.07
    Activations Density 0.005%

    No Known Activations