© 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. 97239
    Prev
    Next
    INDEX
    Explanations

    发

    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
    ッズ
    -0.09
    uldades
    -0.09
    િડ
    -0.09
    lean
    -0.09
     განხ
    -0.08
     leaned
    -0.08
    (le
    -0.08
    nants
    -0.08
    leans
    -0.08
    드는
    -0.08
    POSITIVE LOGITS
    射
    0.12
    出
    0.11
    出的
    0.10
     出
    0.09
    出了
    0.09
     출
    0.09
     gönder
    0.08
    신
    0.07
     Sch
    0.07
    Me
    0.07
    Activations Density 0.002%

    No Known Activations