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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2127
    Prev
    Next
    INDEX
    Explanations

    Verse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fl
    -0.08
     rela
    -0.08
     perl
    -0.08
    pos
    -0.08
     follic
    -0.08
     sore
    -0.07
    στά
    -0.07
    sal
    -0.07
    buddy
    -0.07
     greeted
    -0.07
    POSITIVE LOGITS
     SO
    0.10
    _embedding
    0.08
     ਵਿਕ
    0.08
     सेक
    0.08
    老
    0.07
     Bik
    0.07
     biotech
    0.07
     Wey
    0.07
     Ay
    0.07
     Điều
    0.07
    Activations Density 0.002%

    No Known Activations