© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69272
    Prev
    Next
    INDEX
    Explanations

    steps

    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
     ownership
    -0.08
     કેસ
    -0.08
     exclusions
    -0.08
    ാന
    -0.08
    nullptr
    -0.08
     nihil
    -0.08
     authorized
    -0.07
     renovated
    -0.07
     Ports
    -0.07
     порт
    -0.07
    POSITIVE LOGITS
     cadence
    0.09
     fühl
    0.08
     pounding
    0.08
    感
    0.08
     дых
    0.08
    .detect
    0.08
     marching
    0.08
    踏
    0.08
    �
    0.08
     rhythmic
    0.08
    Activations Density 0.008%

    No Known Activations