© 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. 831
    Prev
    Next
    INDEX
    Explanations

    man

    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
    iov
    -0.08
    peso
    -0.07
    Clinical
    -0.07
    ચાલ
    -0.07
    .Arr
    -0.07
     CAN
    -0.07
     nia
    -0.07
    პ
    -0.07
     тяжел
    -0.07
    机构
    -0.07
    POSITIVE LOGITS
     construction
    0.11
     constructions
    0.11
     constructed
    0.10
     sculptures
    0.10
     lavet
    0.09
    constructed
    0.09
     ನಿರ್ಮ
    0.09
     laget
    0.09
     निर्माण
    0.09
     sculpture
    0.09
    Activations Density 0.010%

    No Known Activations