© 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. 6228
    Prev
    Next
    INDEX
    Explanations

    foot

    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
    推出
    -0.09
     Maker
    -0.09
    创建
    -0.09
    新增
    -0.08
     released
    -0.08
     vznik
    -0.08
     постро
    -0.08
     Linien
    -0.08
    规划
    -0.08
    Forge
    -0.08
    POSITIVE LOGITS
     worship
    0.17
     fetish
    0.17
     licking
    0.16
     admiration
    0.15
     massages
    0.14
    舔
    0.14
     masaje
    0.14
     эрот
    0.13
     smelling
    0.13
     massagens
    0.13
    Activations Density 0.012%

    No Known Activations