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. 60643
    Prev
    Next
    INDEX
    Explanations

    trigonometry

    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
     भर
    -0.08
    பெ
    -0.08
    gestion
    -0.08
    羽
    -0.08
     خو
    -0.08
    Eth
    -0.07
     teklif
    -0.07
     பெ
    -0.07
    बे
    -0.07
    _growth
    -0.07
    POSITIVE LOGITS
    -changing
    0.09
     changing
    0.08
     Changing
    0.08
     periodic
    0.08
     invari
    0.08
     parano
    0.08
    Changing
    0.08
     исчез
    0.07
     Clever
    0.07
    Refreshing
    0.07
    Activations Density 0.034%

    No Known Activations