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

    Neuronpedia

    Jacobian LensNEW
    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. 19-RESID-POST-AA
    11. 19890
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -analysis
    -0.08
    assessment
    -0.08
    where
    -0.08
    ("/")
    -0.08
    Analysis
    -0.07
    FUNCTION
    -0.07
    Assessment
    -0.07
     evaluation
    -0.07
    Evaluation
    -0.07
     assessment
    -0.07
    POSITIVE LOGITS
     ja
    0.09
     iets
    0.08
     сроки
    0.08
    's
    0.08
     άλλ
    0.08
    simp
    0.08
     mana
    0.08
     Já
    0.08
     раньше
    0.08
     рис
    0.07
    Activations Density 0.006%

    No Known Activations