© 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. 712
    Prev
    Next
    INDEX
    Explanations

    the

    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
    -controlled
    -0.08
     współ
    -0.08
     Going
    -0.07
     formular
    -0.07
     Controlled
    -0.07
     Canary
    -0.07
    controlled
    -0.07
     contrô
    -0.07
     controlled
    -0.07
     ``
    -0.07
    POSITIVE LOGITS
    0.08
     mound
    0.08
    дала
    0.08
    Composite
    0.08
     Craig
    0.08
     towering
    0.08
     העצ
    0.08
     pounding
    0.08
    ếm
    0.08
    ถวาย
    0.08
    Activations Density 0.003%
    No Known Activations