© 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. 11-RESID-POST-AA
    11. 78819
    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
    交流
    -0.10
     útiles
    -0.09
     utiles
    -0.09
    透露
    -0.09
     стрем
    -0.09
     útil
    -0.09
     Fortsch
    -0.09
     bedeut
    -0.08
     hoping
    -0.08
     стане
    -0.08
    POSITIVE LOGITS
    _rules
    0.12
     descontos
    0.12
    _discount
    0.11
     rules
    0.11
     начис
    0.11
     discounts
    0.11
    Rules
    0.11
    Discount
    0.11
     Discounts
    0.11
    _rule
    0.11
    Activations Density 0.027%

    No Known Activations