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. 30116
    Prev
    Next
    INDEX
    Explanations

    sports seasons and months

    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
     shedding
    -0.08
     क्लिक
    -0.08
    电�
    -0.08
    üg
    -0.08
     lä
    -0.08
    按钮
    -0.08
     waiting
    -0.07
     antigu
    -0.07
     ticking
    -0.07
     newsp
    -0.07
    POSITIVE LOGITS
     midway
    0.10
     throughout
    0.09
     sepanjang
    0.09
    、中
    0.09
    Throughout
    0.09
    途中
    0.08
     Throughout
    0.08
     halfway
    0.08
    Towards
    0.08
     במהלך
    0.08
    Activations Density 0.067%

    No Known Activations