Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 67999
    Prev
    Next
    INDEX
    Explanations

    cells and mitochondria

    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
     Π
    -0.08
    Tpl
    -0.08
    Π
    -0.08
     τ
    -0.08
    .cid
    -0.07
    gis
    -0.07
     vine
    -0.07
     କ
    -0.07
     Formular
    -0.07
     neus
    -0.07
    POSITIVE LOGITS
     ehemal
    0.10
    曾
    0.10
     voormalige
    0.10
     historically
    0.10
     formerly
    0.10
     ehem
    0.10
     oorspronk
    0.10
     быв
    0.09
    formerly
    0.09
     ehemalige
    0.09
    Activations Density 0.003%

    No Known Activations