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. 44985
    Prev
    Next
    INDEX
    Explanations

    Obligation

    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
     मुद
    -0.09
    Pojo
    -0.09
    apat
    -0.08
     বলতে
    -0.08
    发展的
    -0.08
    byn
    -0.08
     เพื่อ
    -0.08
     জন্য
    -0.08
     হত
    -0.08
    meh
    -0.07
    POSITIVE LOGITS
     노력
    0.08
     fore
    0.07
     воспользоваться
    0.07
     stab
    0.07
     pressure
    0.07
    如下
    0.07
     먼저
    0.07
    ûn
    0.07
     необходимости
    0.07
     bre
    0.07
    Activations Density 0.124%

    No Known Activations