© 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. 47154
    Prev
    Next
    INDEX
    Explanations

    accreditation

    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
     vody
    -0.08
     anne
    -0.08
     restrained
    -0.08
    anne
    -0.08
     Adv
    -0.07
     gord
    -0.07
     Dos
    -0.07
     хозяй
    -0.07
    boats
    -0.07
     torrent
    -0.07
    POSITIVE LOGITS
     accreditation
    0.11
     기관
    0.10
     accredited
    0.09
     Institution
    0.08
    기관
    0.08
     Accreditation
    0.08
    认证
    0.08
     institutions
    0.08
    机构
    0.08
     یافت
    0.08
    Activations Density 0.007%

    No Known Activations