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

    Neuronpedia

    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. 103411
    Prev
    Next
    INDEX
    Explanations

    caught

    np_max-act-logits · gemini-2.0-flash
    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
     Je
    -0.10
    Je
    -0.09
     hdr
    -0.09
     jealousy
    -0.09
     respondeu
    -0.08
     arriving
    -0.08
     arrival
    -0.08
     respondió
    -0.08
     jal
    -0.08
    	J
    -0.08
    POSITIVE LOGITS
     caught
    0.27
    Caught
    0.21
    caught
    0.21
     detected
    0.20
     catching
    0.18
     पक
    0.18
     catches
    0.18
     Catch
    0.18
     discovered
    0.17
     catch
    0.17
    Activations Density 0.013%

    No Known Activations