© 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. 23-RESID-POST-AA
    11. 50707
    Prev
    Next
    INDEX
    Explanations

    say "Citizen"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	del
    -0.09
     perquè
    -0.09
    _del
    -0.09
    oun
    -0.09
    pụ
    -0.08
    ხმარ
    -0.08
    +x
    -0.08
    del
    -0.08
     убед
    -0.08
    +i
    -0.08
    POSITIVE LOGITS
     Cozy
    0.09
     Aires
    0.09
     Esper
    0.08
    	S
    0.08
     ge
    0.08
    Esper
    0.08
     membership
    0.08
    Atlant
    0.08
     cozy
    0.08
     earth
    0.07
    Activations Density 0.001%

    No Known Activations