© 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. 13196
    Prev
    Next
    INDEX
    Explanations

    Um

    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
    เอ
    -0.08
     particulate
    -0.08
    pena
    -0.08
     bau
    -0.07
     rising
    -0.07
     Isaac
    -0.07
    obr
    -0.07
    eine
    -0.07
     narrowly
    -0.07
     expuls
    -0.07
    POSITIVE LOGITS
    antics
    0.08
     yell
    0.08
     prob
    0.08
     devis
    0.08
    姨
    0.07
    偶
    0.07
     Yol
    0.07
     vint
    0.07
     Farrell
    0.07
    Tin
    0.07
    Activations Density 0.002%

    No Known Activations