© 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. 1055
    Prev
    Next
    INDEX
    Explanations

    Kaplan

    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
    ная
    -0.08
     redund
    -0.08
    vær
    -0.08
     Kav
    -0.08
    'origine
    -0.07
    egno
    -0.07
     mgb
    -0.07
     Fais
    -0.07
    ạy
    -0.07
     prohib
    -0.07
    POSITIVE LOGITS
    Creating
    0.09
     Rotary
    0.09
     rotary
    0.09
     tack
    0.08
    _chan
    0.08
     ())
    0.08
     ape
    0.07
    0.07
     Creating
    0.07
    Ble
    0.07
    Activations Density 0.001%
    No Known Activations