© 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. 7-RESID-POST-AA
    11. 758
    Prev
    Next
    INDEX
    Explanations

    chatbot/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     стрел
    -0.09
     투
    -0.09
     પાર
    -0.07
     Annotation
    -0.07
     needles
    -0.07
    reci
    -0.07
     shipment
    -0.07
     needle
    -0.07
    業
    -0.07
     услуги
    -0.07
    POSITIVE LOGITS
     Dy
    0.08
    \t
    0.08
     entrant
    0.08
    Dy
    0.08
    201
    0.07
     Kait
    0.07
     terrest
    0.07
    601
    0.07
    hosts
    0.07
    790
    0.07
    Activations Density 0.000%

    No Known Activations