© 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. 103281
    Prev
    Next
    INDEX
    Explanations

    are

    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
    (await
    -0.08
    rots
    -0.07
    ,y
    -0.07
    2
    -0.07
     kasama
    -0.07
    etween
    -0.07
    rot
    -0.07
    (X
    -0.07
    hoz
    -0.07
    1
    -0.07
    POSITIVE LOGITS
     situaties
    0.10
     disseram
    0.10
     situations
    0.09
     cenário
    0.09
     yleensä
    0.09
    種類
    0.09
     meestal
    0.09
     eindeutig
    0.09
     sèl
    0.09
     varieties
    0.09
    Activations Density 0.003%

    No Known Activations