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

    Neuronpedia

    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. 1107
    Prev
    Next
    INDEX
    Explanations

    competency

    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
     Bernie
    -0.08
     ಆಹ
    -0.08
    illor
    -0.08
    haupt
    -0.08
     counting
    -0.07
    伝
    -0.07
     toque
    -0.07
     transparency
    -0.07
     Saul
    -0.07
     comunicar
    -0.07
    POSITIVE LOGITS
     required
    0.10
     desirable
    0.09
    required
    0.09
    	required
    0.08
     desej
    0.08
    /entity
    0.08
    .des
    0.08
    Ф
    0.08
    ndaky
    0.08
    ARI
    0.07
    Activations Density 0.004%

    No Known Activations