© 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. 29572
    Prev
    Next
    INDEX
    Explanations

    armor of God

    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
    oyu
    -0.08
     hel
    -0.08
     petitions
    -0.08
     শতাংশ
    -0.08
     Torr
    -0.08
     resin
    -0.08
     Reactor
    -0.08
     sonuc
    -0.07
     Primer
    -0.07
     tep
    -0.07
    POSITIVE LOGITS
    装备
    0.14
     Ausstattung
    0.13
     equipped
    0.12
     ausgestattet
    0.12
     оснащ
    0.12
     equipada
    0.12
     equipado
    0.11
     wyposaż
    0.11
    ments
    0.11
     outf
    0.11
    Activations Density 0.028%

    No Known Activations