© 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. 75527
    Prev
    Next
    INDEX
    Explanations

    climate change and justice

    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
    ិត្ត
    -0.08
     tón
    -0.08
     Gossip
    -0.08
    Enc
    -0.08
    ienz
    -0.08
    ysig
    -0.08
    -------------</
    -0.07
    ystall
    -0.07
    νον
    -0.07
    ազմ
    -0.07
    POSITIVE LOGITS
     vuln
    0.10
     vulnerability
    0.09
     disproportionately
    0.09
     vulner
    0.09
     vulnerable
    0.09
     गरीब
    0.09
     Vulner
    0.08
     disproportion
    0.08
     vulnerabilities
    0.08
    偏
    0.08
    Activations Density 0.027%

    No Known Activations