© 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. 103594
    Prev
    Next
    INDEX
    Explanations

    :

    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
     zweiten
    -0.10
    pecific
    -0.10
     speziellen
    -0.10
     dritten
    -0.09
     části
    -0.09
     spezif
    -0.09
    另一
    -0.09
     Certain
    -0.09
     innerhalb
    -0.08
    	second
    -0.08
    POSITIVE LOGITS
     when
    0.10
     જ્યારે
    0.10
     όταν
    0.10
    When
    0.09
     当
    0.09
    when
    0.09
    :↵
    0.09
     जब
    0.09
     როდესაც
    0.09
    ():↵
    0.08
    Activations Density 0.032%

    No Known Activations