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. 119347
    Prev
    Next
    INDEX
    Explanations

    chess notation

    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
     xã
    -0.08
    230
    -0.07
     הש
    -0.07
     kantoor
    -0.07
    ратить
    -0.07
     בתחום
    -0.07
     בארץ
    -0.07
    destination
    -0.07
    ailing
    -0.07
     אד
    -0.07
    POSITIVE LOGITS
     ésta
    0.08
     comunicaciones
    0.08
    Tit
    0.08
     bouch
    0.08
     હુમ
    0.08
     cartas
    0.08
     ત્યાર
    0.08
    Latch
    0.08
    ানোর
    0.08
    িত্য
    0.07
    Activations Density 0.001%

    No Known Activations