© 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. 11-RESID-POST-AA
    11. 24626
    Prev
    Next
    INDEX
    Explanations

    How

    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
    (if
    -0.09
    (enabled
    -0.08
    (Collection
    -0.08
     oso
    -0.08
     së
    -0.08
     القرن
    -0.08
     ogen
    -0.08
     mainland
    -0.08
     ис
    -0.08
     engu
    -0.08
    POSITIVE LOGITS
     Pers
    0.08
     Discuss
    0.08
     спраш
    0.08
     Pom
    0.07
     попрос
    0.07
    Email
    0.07
     transcripts
    0.07
     -*-
    0.07
    Discuss
    0.07
     discussing
    0.07
    Activations Density 0.134%

    No Known Activations