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. 87835
    Prev
    Next
    INDEX
    Explanations

    Object

    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
     Skate
    -0.08
    ontal
    -0.08
    载
    -0.08
     kër
    -0.07
     Acura
    -0.07
    LOPT
    -0.07
     बाइक
    -0.07
     thị
    -0.07
     skate
    -0.07
     Clarkson
    -0.07
    POSITIVE LOGITS
    Expires
    0.08
     achievement
    0.08
    Achievement
    0.08
     الوقت
    0.07
    �
    0.07
    Negative
    0.07
     logro
    0.07
     الآخر
    0.07
     breakthrough
    0.07
    Duplicates
    0.07
    Activations Density 0.001%

    No Known Activations