Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 314
    Prev
    Next
    INDEX
    Explanations

    End of events/periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grou
    -0.08
     organizations
    -0.07
     later
    -0.07
    虹
    -0.07
    �
    -0.07
    Однако
    -0.07
     самом
    -0.07
     Helm
    -0.07
     lighting
    -0.07
    АП
    -0.07
    POSITIVE LOGITS
     समाप्त
    0.11
     expediente
    0.10
     selesai
    0.10
     ముగ
    0.10
     заканч
    0.09
     satisfactor
    0.09
     interrupted
    0.09
     periodo
    0.09
    終了
    0.09
     അവസാന
    0.09
    Activations Density 0.125%

    No Known Activations