© 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. 19-RESID-POST-AA
    11. 102820
    Prev
    Next
    INDEX
    Explanations

    say "Y"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _di
    -0.08
     наполн
    -0.08
     computational
    -0.08
     DI
    -0.08
     <>",
    -0.08
    预测软件
    -0.08
     posame
    -0.08
     вычис
    -0.08
     специал
    -0.08
     quantit
    -0.07
    POSITIVE LOGITS
    Y
    0.10
    -स
    0.09
    ("%
    0.09
    /%
    0.09
    .%
    0.09
    년
    0.08
    Η
    0.08
    �
    0.08
    يوب
    0.08
     ]),↵
    0.08
    Activations Density 0.001%

    No Known Activations