© 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. 7-RESID-POST-AA
    6. 722
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Odyssey
    -0.09
     Ony
    -0.08
    otrans
    -0.08
     cerebral
    -0.08
     appreciating
    -0.08
    וג
    -0.07
     fungus
    -0.07
     OV
    -0.07
     onc
    -0.07
     Anti
    -0.07
    POSITIVE LOGITS
    fft
    0.09
     Earth's
    0.08
     amph
    0.08
     sober
    0.08
     terd
    0.08
     Lau
    0.08
     cham
    0.08
     dije
    0.07
     bak
    0.07
     hatta
    0.07
    Activations Density 0.032%

    No Known Activations