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. 78649
    Prev
    Next
    INDEX
    Explanations

    farm

    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
     cobr
    -0.08
    十
    -0.08
     helic
    -0.08
     المسلحة
    -0.07
     stare
    -0.07
    �
    -0.07
    itsi
    -0.07
    ovs
    -0.07
    paren
    -0.07
     bina
    -0.07
    POSITIVE LOGITS
    stead
    0.10
    用品
    0.10
    wreck
    0.08
    /business
    0.08
     खराब
    0.08
    yard
    0.08
    家乐
    0.08
     Agriculture
    0.08
    �
    0.07
    業
    0.07
    Activations Density 0.012%

    No Known Activations