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. 44085
    Prev
    Next
    INDEX
    Explanations

    ic

    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
    पू
    -0.09
     Experienced
    -0.08
    powered
    -0.08
    ့
    -0.08
    pour
    -0.08
     Goes
    -0.08
    Saya
    -0.08
    Full
    -0.08
     Julio
    -0.08
    pas
    -0.08
    POSITIVE LOGITS
     trans
    0.08
    -ra
    0.08
    word
    0.08
    hton
    0.08
    交易
    0.07
     figur
    0.07
     audi
    0.07
     rendelkez
    0.07
     nouveau
    0.07
     digits
    0.07
    Activations Density 0.002%

    No Known Activations