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. 19350
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
     posting
    -0.08
     dime
    -0.08
     invis
    -0.07
     dejo
    -0.07
     broadcasting
    -0.07
     awarding
    -0.07
     owning
    -0.07
     trium
    -0.07
     assertion
    -0.07
    -related
    -0.07
    POSITIVE LOGITS
     unfamiliar
    0.12
     ознаком
    0.11
     להבין
    0.11
     বুঝ
    0.11
     հասկ
    0.11
     apprendre
    0.11
     hesitant
    0.11
     सीख
    0.10
     kennism
    0.10
    了解到
    0.10
    Activations Density 0.070%

    No Known Activations