© 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. 54656
    Prev
    Next
    INDEX
    Explanations

    wifi and network troubleshooting

    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
     approachable
    -0.08
     obligator
    -0.08
     introductory
    -0.08
     whimsical
    -0.07
     quasi
    -0.07
     molten
    -0.07
    javax
    -0.07
    mass
    -0.07
    倫理
    -0.07
    illegal
    -0.07
    POSITIVE LOGITS
     deterior
    0.09
     તમારા
    0.09
    电脑
    0.09
     તમે
    0.09
     جودة
    0.09
     જુઓ
    0.09
     bott
    0.08
     שלכם
    0.08
     మీరు
    0.08
     Fortnite
    0.08
    Activations Density 0.010%

    No Known Activations