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. 54251
    Prev
    Next
    INDEX
    Explanations

    solving math problems

    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
    Compilation
    -0.08
    专题
    -0.08
     compilation
    -0.08
    Sempre
    -0.08
     interna
    -0.08
     Compilation
    -0.08
     semper
    -0.08
     missa
    -0.07
     prestations
    -0.07
     följ
    -0.07
    POSITIVE LOGITS
    _candidate
    0.11
     viable
    0.11
     candidates
    0.11
    andidates
    0.10
    找到
    0.10
    _candidates
    0.10
    (candidate
    0.10
    符合
    0.10
     подходят
    0.10
     ઉમેદ
    0.10
    Activations Density 0.137%

    No Known Activations