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. 111853
    Prev
    Next
    INDEX
    Explanations

    mache

    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
     comparable
    -0.08
     exchanged
    -0.08
    Selecion
    -0.08
     Exchange
    -0.07
     exchange
    -0.07
     exchanges
    -0.07
    exchange
    -0.07
    Liquidity
    -0.07
    Exchange
    -0.07
     accommodation
    -0.07
    POSITIVE LOGITS
    容易
    0.09
     Gewalt
    0.08
    施工
    0.08
     WWF
    0.08
    扫
    0.08
     schn
    0.08
     boule
    0.08
     cé
    0.08
    群众
    0.08
     eisen
    0.08
    Activations Density 0.001%

    No Known Activations