© 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. 95364
    Prev
    Next
    INDEX
    Explanations

    Loss of privileges

    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
    bestand
    -0.08
    guise
    -0.07
    regexp
    -0.07
    ൂ
    -0.07
    لاقات
    -0.07
    duc
    -0.07
    ిబ
    -0.07
    verige
    -0.07
    jumlah
    -0.07
    setzungen
    -0.07
    POSITIVE LOGITS
    处罚
    0.12
     наказ
    0.12
     punitive
    0.12
     punishment
    0.11
     punished
    0.11
     punish
    0.11
     penalties
    0.10
     offending
    0.10
     penalty
    0.10
     штраф
    0.10
    Activations Density 0.121%

    No Known Activations