© 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. 45
    Prev
    Next
    INDEX
    Explanations

    Finishing steps

    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
    াথমিক
    -0.08
     конструк
    -0.08
     applicability
    -0.08
     받을
    -0.08
    范
    -0.08
     사용할
    -0.07
    되는
    -0.07
    ظم
    -0.07
     allein
    -0.07
     оди
    -0.07
    POSITIVE LOGITS
     polishing
    0.13
    Finalize
    0.12
     finalize
    0.12
    完善
    0.11
     finais
    0.11
     polish
    0.11
     refin
    0.11
     refinement
    0.10
    _finalize
    0.10
     refining
    0.10
    Activations Density 0.027%

    No Known Activations