© 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. 103074
    Prev
    Next
    INDEX
    Explanations

    say "parser"

    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
     sought
    -0.09
     همه
    -0.09
     Dacă
    -0.08
     Jika
    -0.08
     چشم
    -0.08
     모든
    -0.08
    ണമെന്നും
    -0.08
    ыдущ
    -0.08
     Якщо
    -0.08
     seek
    -0.08
    POSITIVE LOGITS
     popul
    0.10
     filling
    0.08
    填
    0.08
     fillings
    0.08
    添加
    0.08
     populate
    0.08
    populate
    0.08
     fills
    0.07
    YEAR
    0.07
     adaptations
    0.07
    Activations Density 0.002%

    No Known Activations