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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103044
    Prev
    Next
    INDEX
    Explanations

    fluff

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     उच्च
    -0.09
     zowel
    -0.08
     दो
    -0.08
     दोनों
    -0.08
     yüksek
    -0.08
     高
    -0.07
     hoher
    -0.07
     भर
    -0.07
     высокого
    -0.07
     Registration
    -0.07
    POSITIVE LOGITS
     fluff
    0.16
     fluffy
    0.11
     тарқ
    0.10
    fl
    0.09
     fan
    0.09
    播播
    0.09
     loosen
    0.09
     вент
    0.09
    เปิด
    0.09
    рып
    0.09
    Activations Density 0.002%

    No Known Activations