Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45185
    Prev
    Next
    INDEX
    Explanations

    gates

    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
     Mansfield
    -0.08
     rocking
    -0.08
     landlords
    -0.08
    ,多
    -0.08
    锐
    -0.07
     carc
    -0.07
     Caribbean
    -0.07
     stiffness
    -0.07
    hes
    -0.07
     Kepala
    -0.07
    POSITIVE LOGITS
     altru
    0.08
     philanthrop
    0.08
     philanth
    0.08
     philanthropic
    0.08
    -disable
    0.08
    akk
    0.08
    -download
    0.07
     Wikip
    0.07
    freund
    0.07
    ۔
    0.07
    Activations Density 0.005%

    No Known Activations