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. 15-RESID-POST-AA
    6. 19334
    Prev
    Next
    INDEX
    Explanations

    ways to say eat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    604
    -0.08
    -0.07
    532
    -0.07
    684
    -0.07
    60
    -0.07
    200
    -0.07
    612
    -0.07
     Exactly
    -0.07
    199
    -0.07
     Its
    -0.07
    POSITIVE LOGITS
     খাব
    0.11
     snacks
    0.10
     eat
    0.10
     boire
    0.10
     понадоб
    0.09
    饮
    0.09
    حتاج
    0.09
     يحتاج
    0.09
     nanti
    0.09
     necesitar
    0.09
    Activations Density 0.108%

    No Known Activations