© 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. 50603
    Prev
    Next
    INDEX
    Explanations

    -

    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
    (q
    -0.09
    (dr
    -0.09
    (PRO
    -0.09
    (Q
    -0.09
    (am
    -0.09
    (Class
    -0.08
    (component
    -0.08
    _am
    -0.08
    (exp
    -0.08
    (C
    -0.08
    POSITIVE LOGITS
     Toe
    0.12
     Toen
    0.11
     Tooth
    0.10
    toe
    0.10
     toen
    0.10
     cheek
    0.10
    Toe
    0.10
     toe
    0.10
    -hand
    0.09
     TOE
    0.09
    Activations Density 0.006%

    No Known Activations