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. 43232
    Prev
    Next
    INDEX
    Explanations

    past tense

    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
     díky
    -0.08
     outlining
    -0.08
    thanks
    -0.08
    lerle
    -0.08
     proc
    -0.08
     woman's
    -0.08
     благодаря
    -0.07
    etel
    -0.07
     descrição
    -0.07
     graças
    -0.07
    POSITIVE LOGITS
     disappointment
    0.18
     disappointed
    0.17
     enttä
    0.15
     Verlust
    0.14
     disappointing
    0.14
     disappoint
    0.14
     loss
    0.14
     kehilangan
    0.14
     saddened
    0.14
    Loss
    0.13
    Activations Density 0.129%

    No Known Activations