© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 50596
    Prev
    Next
    INDEX
    Explanations

    闭

    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
     fina
    -0.08
     දෙ
    -0.08
     boldy
    -0.08
    çinin
    -0.08
     naast
    -0.07
    치
    -0.07
    binary
    -0.07
    bureau
    -0.07
     abaixo
    -0.07
    imik
    -0.07
    POSITIVE LOGITS
    环
    0.15
    合
    0.14
    路
    0.12
     ल
    0.12
     ল
    0.12
    合彩
    0.12
     લ
    0.11
    源
    0.10
     合
    0.10
    環
    0.10
    Activations Density 0.001%

    No Known Activations