© 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. 23-RESID-POST-AA
    11. 6072
    Prev
    Next
    INDEX
    Explanations

    n

    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
     presidente
    -0.08
     strip
    -0.07
    ага
    -0.07
     Arb
    -0.07
     faible
    -0.07
     अर्ज
    -0.07
     André
    -0.07
    андр
    -0.07
     agrade
    -0.07
     perch
    -0.07
    POSITIVE LOGITS
     نزدیک
    0.09
    istika
    0.09
    alisme
    0.09
    quals
    0.09
    ativen
    0.08
    alis
    0.08
     sucks
    0.08
     ভুল
    0.08
     wus
    0.08
    kuha
    0.08
    Activations Density 0.000%

    No Known Activations