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. 23-RESID-POST-AA
    6. 130886
    Prev
    Next
    INDEX
    Explanations

    say "ances"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bruis
    -0.08
     uim
    -0.08
    ीडिया
    -0.08
    osition
    -0.07
     rob
    -0.07
    ぼ
    -0.07
     shoulders
    -0.07
     glu
    -0.07
     ida
    -0.07
    োজ
    -0.07
    POSITIVE LOGITS
    ances
    0.20
    ance
    0.17
    ANCE
    0.15
    ANCES
    0.14
    ancen
    0.13
    anced
    0.13
    ancing
    0.12
    anc
    0.12
    ancements
    0.11
    ancé
    0.11
    Activations Density 0.002%

    No Known Activations