Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 75957
    Prev
    Next
    INDEX
    Explanations

    map generation

    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
     acupuncture
    -0.08
    yorum
    -0.08
     buah
    -0.08
    detalle
    -0.08
    Mention
    -0.08
    Detalle
    -0.08
     colorectal
    -0.07
     analges
    -0.07
     solicitation
    -0.07
     muzzle
    -0.07
    POSITIVE LOGITS
     lake
    0.10
     drought
    0.09
    湖
    0.09
     lakes
    0.09
     river
    0.08
     tendency
    0.08
     borders
    0.08
     নদ
    0.08
    大陆
    0.08
     bordering
    0.08
    Activations Density 0.002%

    No Known Activations