Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54153
    Prev
    Next
    INDEX
    Explanations

    Limit

    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
     tenure
    -0.08
    Market
    -0.08
     overly
    -0.07
    市場
    -0.07
     sy
    -0.07
     eigen
    -0.07
     вывод
    -0.07
    #{
    -0.07
     proprietary
    -0.07
    sy
    -0.07
    POSITIVE LOGITS
    amaha
    0.09
    ঞ্জ
    0.09
     Timing
    0.08
     Automatic
    0.08
     Babys
    0.08
    itime
    0.08
     Секс
    0.08
     automatique
    0.08
     Apartments
    0.08
     Conversations
    0.08
    Activations Density 0.000%

    No Known Activations