© 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. 51686
    Prev
    Next
    INDEX
    Explanations

    say read

    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
     Servlet
    -0.10
    ALSE
    -0.08
    (Servlet
    -0.08
    Jwt
    -0.08
    .Servlet
    -0.08
    alled
    -0.08
    ภู
    -0.08
    _Pin
    -0.08
     ekte
    -0.08
     सिक
    -0.08
    POSITIVE LOGITS
     sade
    0.11
     minim
    0.10
     fs
    0.10
     readline
    0.09
     ora
    0.09
    Ora
    0.09
     kleur
    0.09
     Minim
    0.09
     otim
    0.09
    Salut
    0.09
    Activations Density 0.002%

    No Known Activations