© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43520
    Prev
    Next
    INDEX
    Explanations

    Math proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dn
    -0.08
    -0.08
     bost
    -0.08
    Agent
    -0.08
     abe
    -0.08
    ))))↵↵
    -0.08
     zuvor
    -0.07
     seben
    -0.07
     sozial
    -0.07
    histor
    -0.07
    POSITIVE LOGITS
     acquaintance
    0.09
    Notation
    0.09
     hereby
    0.08
    Fancy
    0.08
     Our
    0.08
     Fakult
    0.07
     AMC
    0.07
     We're
    0.07
     Arbitr
    0.07
     lemma
    0.07
    Activations Density 0.051%
    No Known Activations