© 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. 50317
    Prev
    Next
    INDEX
    Explanations

    say "space"

    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
    luv
    -0.09
    愛い
    -0.08
     enemigos
    -0.08
     գաղափ
    -0.08
    okable
    -0.08
    itekerezo
    -0.08
    -Par
    -0.08
    ógico
    -0.08
     Apex
    -0.08
     aihe
    -0.08
    POSITIVE LOGITS
     body
    0.14
     space
    0.13
    (body
    0.12
     main
    0.12
    Body
    0.12
    body
    0.12
    Space
    0.11
     long
    0.11
     Space
    0.11
     Var
    0.11
    Activations Density 0.035%

    No Known Activations