© 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. 2976
    Prev
    Next
    INDEX
    Explanations

    script

    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
     Hector
    -0.09
     дело
    -0.08
     tuss
    -0.08
     मेड
    -0.08
    cron
    -0.08
    HK
    -0.08
     zwe
    -0.08
    HV
    -0.08
    Hv
    -0.08
    _hw
    -0.08
    POSITIVE LOGITS
     Lar
    0.10
    493
    0.08
     thermal
    0.08
     lar
    0.08
     indicative
    0.07
    จัด
    0.07
     기준
    0.07
     ions
    0.07
     Evaluate
    0.07
    inations
    0.07
    Activations Density 0.000%

    No Known Activations