© 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 EvalsExportsinterp-engineNEWAPI 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. 18590
    Prev
    Next
    INDEX
    Explanations

    say "action"

    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
    BE
    -0.09
    Db
    -0.08
    until
    -0.08
    ARRAY
    -0.08
    issa
    -0.08
    Shown
    -0.08
    LOW
    -0.08
    INDEX
    -0.08
    VI
    -0.08
    credited
    -0.08
    POSITIVE LOGITS
     action
    0.21
     ação
    0.21
     acción
    0.20
     действие
    0.18
    ’action
    0.18
     actie
    0.18
    	action
    0.17
    'action
    0.17
     कार्रवाई
    0.17
    行动
    0.16
    Activations Density 0.004%

    No Known Activations