© 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. 64541
    Prev
    Next
    INDEX
    Explanations

    geometric shapes

    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
    ែរ
    -0.09
     ហ
    -0.08
     atoi
    -0.08
    allo
    -0.08
    enqueue
    -0.08
     Silva
    -0.08
    фарма
    -0.08
    infeld
    -0.08
    enny
    -0.07
    ើយ
    -0.07
    POSITIVE LOGITS
    ตรง
    0.08
     aligns
    0.08
     aligned
    0.07
     которого
    0.07
     refriger
    0.07
     donated
    0.07
    :left
    0.07
     Align
    0.07
     которой
    0.07
     oc
    0.07
    Activations Density 0.048%

    No Known Activations