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. 58407
    Prev
    Next
    INDEX
    Explanations

    one, no

    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
    .enumer
    -0.08
     Sp
    -0.07
     дисцип
    -0.07
     lots
    -0.07
     Bari
    -0.07
     espec
    -0.07
     Theo
    -0.07
    Сп
    -0.07
    .splice
    -0.07
     ample
    -0.07
    POSITIVE LOGITS
     koskaan
    0.12
     okenn
    0.12
     mitään
    0.10
     enää
    0.10
     nor
    0.10
     ποτέ
    0.10
     nikdy
    0.10
     längre
    0.09
     کوئی
    0.09
     pernah
    0.09
    Activations Density 0.012%

    No Known Activations