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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1338
    Prev
    Next
    INDEX
    Explanations

    Lage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🏼
    -0.08
     بق
    -0.07
     plas
    -0.07
    ोरी
    -0.07
     CCM
    -0.07
    .cmb
    -0.07
     blanco
    -0.07
     BH
    -0.07
    onn
    -0.07
     distracted
    -0.07
    POSITIVE LOGITS
     agit
    0.08
     pł
    0.07
     occasion
    0.07
     peri
    0.07
     rendre
    0.07
    iaomi
    0.07
     квартиры
    0.07
    iku
    0.07
     หล
    0.07
     emoc
    0.07
    Activations Density 0.001%

    No Known Activations