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. 76054
    Prev
    Next
    INDEX
    Explanations

    medical/scientific procedures

    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
     tels
    -0.09
    -0.08
    waka
    -0.08
    �్థిత
    -0.08
    WATCH
    -0.08
     tieto
    -0.07
     Brent
    -0.07
     utama
    -0.07
     Shot
    -0.07
     ತಪ್ಪ
    -0.07
    POSITIVE LOGITS
     interchangeable
    0.08
     Ull
    0.08
     flattened
    0.08
     �
    0.08
     abrasive
    0.08
    нас
    0.07
    	task
    0.07
    inz
    0.07
    邦
    0.07
     ashes
    0.07
    Activations Density 0.000%

    No Known Activations