© 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. 79193
    Prev
    Next
    INDEX
    Explanations

    security and difficulty

    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
     kür
    -0.08
     də
    -0.07
    	found
    -0.07
    .ok
    -0.07
    ować
    -0.07
     granddaughter
    -0.07
     patria
    -0.07
     fleurs
    -0.07
    _found
    -0.07
     earthy
    -0.07
    POSITIVE LOGITS
     deterr
    0.12
     unlikely
    0.11
     deter
    0.11
     compelled
    0.11
     يجعل
    0.10
     inability
    0.10
     ولن
    0.10
     attackers
    0.10
     impedir
    0.10
     onmogelijk
    0.10
    Activations Density 0.056%

    No Known Activations