© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129282
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     collars
    -0.08
    居民
    -0.08
     atas
    -0.08
     incandescent
    -0.08
     tary
    -0.08
     descendants
    -0.08
     slabs
    -0.08
    _eq
    -0.08
     atre
    -0.08
     nascimento
    -0.08
    POSITIVE LOGITS
     skills
    0.17
     навы
    0.15
     habilidades
    0.15
    技能
    0.14
     Fähigkeiten
    0.14
     teamwork
    0.14
    skills
    0.14
     Skills
    0.13
     vaardigheden
    0.13
    Skills
    0.13
    Activations Density 0.037%

    No Known Activations