© 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. 3-RESID-POST-AA
    11. 2568
    Prev
    Next
    INDEX
    Explanations

    interpret

    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
    Alarm
    -0.09
     Megan
    -0.08
     anthrop
    -0.08
     Zn
    -0.08
     Anthrop
    -0.08
    alarm
    -0.08
     Leah
    -0.08
     anaer
    -0.07
    Zn
    -0.07
    ଗ
    -0.07
    POSITIVE LOGITS
     પુ
    0.09
    824
    0.08
     twig
    0.08
     braid
    0.08
     cre
    0.07
     winery
    0.07
    brick
    0.07
     Winery
    0.07
    cre
    0.07
    insen
    0.07
    Activations Density 0.004%

    No Known Activations