© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108208
    Prev
    Next
    INDEX
    Explanations

    Dereferencing

    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
     newcom
    -0.10
    эк
    -0.09
     smok
    -0.08
     Маш
    -0.08
     signatures
    -0.08
     exponentially
    -0.08
    necessarily
    -0.07
    وعة
    -0.07
    Expo
    -0.07
    /copyleft
    -0.07
    POSITIVE LOGITS
    ierungs
    0.08
     accessible
    0.08
    olge
    0.07
     bears
    0.07
     julgamento
    0.07
     ascertain
    0.07
     oppression
    0.07
     dere
    0.07
    ानि
    0.07
     overhead
    0.07
    Activations Density 0.001%

    No Known Activations