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. 102825
    Prev
    Next
    INDEX
    Explanations

    the

    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
    K
    -0.08
    Skin
    -0.08
    Crunch
    -0.08
     fb
    -0.07
     ਕੰ
    -0.07
     Kant
    -0.07
    TC
    -0.07
    fb
    -0.07
    Recorder
    -0.07
    ekin
    -0.07
    POSITIVE LOGITS
    另外
    0.11
     الـ
    0.10
     restantes
    0.10
     നാല്
    0.09
     બધા
    0.09
     остальных
    0.09
     četiri
    0.08
     dört
    0.08
     rehetra
    0.08
    .experimental
    0.08
    Activations Density 0.066%

    No Known Activations