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. 386
    Prev
    Next
    INDEX
    Explanations

    water

    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
    (es
    -0.08
     rubber
    -0.08
    Rede
    -0.08
     Lia
    -0.08
    Shar
    -0.08
     pavement
    -0.07
     ego
    -0.07
    kf
    -0.07
    psz
    -0.07
     tow
    -0.07
    POSITIVE LOGITS
    works
    0.10
    logged
    0.10
     vapor
    0.09
    bank
    0.08
    (水
    0.08
     marinade
    0.07
     Coral
    0.07
    borne
    0.07
     curing
    0.07
    melon
    0.07
    Activations Density 0.043%

    No Known Activations