© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2514
    Prev
    Next
    INDEX
    Explanations

    Referendums/Elections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     billi
    -0.08
    охран
    -0.08
    Vid
    -0.08
     Cole
    -0.08
     Vid
    -0.08
     discip
    -0.07
    ுள்ளார்
    -0.07
     spray
    -0.07
     Vij
    -0.07
     DOS
    -0.07
    POSITIVE LOGITS
     sulla
    0.09
     auf
    0.08
    ummi
    0.08
     cud
    0.08
    bok
    0.08
    mandatory
    0.08
     preguntar
    0.08
    (blob
    0.08
     Mandatory
    0.08
     antic
    0.07
    Activations Density 0.010%

    No Known Activations