© 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. 99182
    Prev
    Next
    INDEX
    Explanations

    implementation tips

    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
     llega
    -0.08
     Leon
    -0.08
     copyrights
    -0.08
     toch
    -0.08
    _fake
    -0.07
     kilometer
    -0.07
     policiais
    -0.07
     Contents
    -0.07
     Password
    -0.07
     Copyright
    -0.07
    POSITIVE LOGITS
    以上
    0.11
    上述
    0.10
    综合
    0.10
    这些
    0.10
     इन्ह
    0.09
    These
    0.09
     ఇవ
    0.09
     These
    0.08
     এসব
    0.08
    不断
    0.08
    Activations Density 0.115%

    No Known Activations