© 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. 3026
    Prev
    Next
    INDEX
    Explanations

    can

    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
    Mex
    -0.09
     কা�
    -0.09
    /custom
    -0.09
    forth
    -0.08
     Local
    -0.08
    ouw
    -0.08
     Brust
    -0.08
     locali
    -0.08
    yage
    -0.08
     কার
    -0.08
    POSITIVE LOGITS
     pointed
    0.08
     abas
    0.07
     ಅತ್ಯ
    0.07
     honour
    0.07
    用途
    0.07
    tear
    0.07
    iyalar
    0.07
     talen
    0.07
    onder
    0.07
     pros
    0.07
    Activations Density 0.081%

    No Known Activations