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. 106096
    Prev
    Next
    INDEX
    Explanations

    .

    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
     снижение
    -0.08
     aborto
    -0.07
     Cyrus
    -0.07
     فناوری
    -0.07
     جرم
    -0.07
     neighborhoods
    -0.07
     heath
    -0.07
     worth
    -0.07
     پژوه
    -0.07
     عملکرد
    -0.07
    POSITIVE LOGITS
     दें
    0.09
    kwa
    0.08
    tho
    0.08
     तार
    0.07
     obligatoire
    0.07
     להתח
    0.07
    उत्तर
    0.07
     oblig
    0.07
     decorate
    0.07
    回复
    0.07
    Activations Density 0.013%

    No Known Activations