© 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. 19-RESID-POST-AA
    11. 103046
    Prev
    Next
    INDEX
    Explanations

    disparate topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -0.09
     can
    -0.09
    只能
    -0.09
     "
    -0.09
     so
    -0.09
     must
    -0.09
     \(
    -0.09
     can't
    -0.08
     بحيث
    -0.08
    :↵↵
    -0.08
    POSITIVE LOGITS
     significativamente
    0.11
     efficacement
    0.10
     sooner
    0.10
    ärkung
    0.10
     stär
    0.10
     Improving
    0.10
    	goto
    0.09
     výraz
    0.09
     zunehmend
    0.09
     davantage
    0.09
    Activations Density 0.084%

    No Known Activations