© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99165
    Prev
    Next
    INDEX
    Explanations

    ---

    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
     장
    -0.08
     vines
    -0.07
     vine
    -0.07
     Rug
    -0.07
     leon
    -0.07
    imoto
    -0.07
    Gren
    -0.07
     Vine
    -0.07
     lach
    -0.07
     VD
    -0.07
    POSITIVE LOGITS
     bore
    0.08
     Pat
    0.07
     Lane
    0.07
    ਆ
    0.07
    dq
    0.07
    AMS
    0.07
     commons
    0.07
     adm
    0.07
     intrigu
    0.07
    irc
    0.07
    Activations Density 0.012%

    No Known Activations