© 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. 11-RESID-POST-AA
    11. 44696
    Prev
    Next
    INDEX
    Explanations

    hook

    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
     advocate
    -0.09
    _expand
    -0.08
     advocating
    -0.08
     tijdens
    -0.08
    omentum
    -0.07
     Advocacy
    -0.07
     Brisbane
    -0.07
    cks
    -0.07
    _unique
    -0.07
     negociar
    -0.07
    POSITIVE LOGITS
    Calibri
    0.09
     Players
    0.08
     friends
    0.08
     Jacob
    0.08
     remont
    0.08
     NAD
    0.08
     কার
    0.07
     ongem
    0.07
     Mad
    0.07
     Rog
    0.07
    Activations Density 0.002%

    No Known Activations