© 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. 30935
    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
    Invalidate
    -0.08
     invalidate
    -0.08
    _DELAY
    -0.08
    �
    -0.08
    очно
    -0.07
    姐
    -0.07
     particuli
    -0.07
    留下
    -0.07
      ↵    ↵
    -0.07
     sting
    -0.07
    POSITIVE LOGITS
     UNICEF
    0.09
     dla
    0.08
     توسط
    0.08
     Jean
    0.08
     Zhu
    0.08
    ibid
    0.08
     Lak
    0.08
     Zara
    0.08
     Axel
    0.08
     Carlton
    0.08
    Activations Density 0.083%

    No Known Activations