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. 77395
    Prev
    Next
    INDEX
    Explanations

    angle

    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
     chop
    -0.08
    sta
    -0.08
    -hour
    -0.08
     lazy
    -0.07
     verification
    -0.07
    Lazy
    -0.07
    _hour
    -0.07
     মাঝ
    -0.07
     zmian
    -0.07
     Lazy
    -0.07
    POSITIVE LOGITS
    alida
    0.08
    电视
    0.08
    embership
    0.08
     Boyd
    0.08
     televisão
    0.08
     presidencial
    0.07
     Tabellen
    0.07
    》和
    0.07
    	props
    0.07
     использовании
    0.07
    Activations Density 0.002%

    No Known Activations