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. 53886
    Prev
    Next
    INDEX
    Explanations

    astronomy, gardening, weather

    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
     énerg
    -0.08
    UME
    -0.08
     કંપની
    -0.08
    _COLL
    -0.08
     yrity
    -0.07
    _Is
    -0.07
    企業
    -0.07
    _PK
    -0.07
     headline
    -0.07
     ach
    -0.07
    POSITIVE LOGITS
    លោក
    0.08
    ectomy
    0.08
     trakt
    0.08
    pheric
    0.08
    Singer
    0.08
     bedrooms
    0.08
    باشد
    0.07
     Luka
    0.07
    Kyle
    0.07
    утств
    0.07
    Activations Density 0.002%

    No Known Activations