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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 29999
    Prev
    Next
    INDEX
    Explanations

    Story excerpts

    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
    bí
    -0.08
    wizard
    -0.08
    creto
    -0.08
     indes
    -0.08
     porcelain
    -0.08
    sym
    -0.08
     hati
    -0.08
    ugal
    -0.07
    rael
    -0.07
     struktur
    -0.07
    POSITIVE LOGITS
    Searching
    0.10
     patrol
    0.09
     buscando
    0.09
     поис
    0.09
     búsqueda
    0.08
    寻找
    0.08
     Patrol
    0.08
     greve
    0.08
     recreational
    0.08
     ಹುಡು
    0.08
    Activations Density 0.055%

    No Known Activations