© 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. 23-RESID-POST-AA
    11. 96749
    Prev
    Next
    INDEX
    Explanations

    D

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Januar
    -0.08
     האם
    -0.08
    onnaise
    -0.08
     televisão
    -0.08
     FIF
    -0.08
    insdag
    -0.08
     bikini
    -0.08
    ouvrir
    -0.08
     फेसबुक
    -0.08
     Facebook
    -0.07
    POSITIVE LOGITS
    ungeons
    0.17
    &D
    0.14
    ungeon
    0.12
    ंजन
    0.12
    ND
    0.12
    न्ज
    0.12
    �্জ
    0.11
    ঞ্জ
    0.11
    ಂಜ
    0.10
    Dungeon
    0.10
    Activations Density 0.006%

    No Known Activations