© 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. 3-RESID-POST-AA
    11. 3157
    Prev
    Next
    INDEX
    Explanations

    Gulliver's Travels/CAD software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tarif
    -0.08
     reservoirs
    -0.08
     kasus
    -0.08
    reserv
    -0.08
    istik
    -0.07
     LLP
    -0.07
     sistem
    -0.07
    犬
    -0.07
    	packet
    -0.07
    LOT
    -0.07
    POSITIVE LOGITS
    .beh
    0.08
    .Version
    0.07
     Hed
    0.07
    .now
    0.07
     гуман
    0.07
    .on
    0.07
    fono
    0.07
    .VERSION
    0.07
    nie
    0.07
    .Kind
    0.07
    Activations Density 0.001%

    No Known Activations