© 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. 24739
    Prev
    Next
    INDEX
    Explanations

    consistent

    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
     bear
    -0.08
     Sule
    -0.08
    amantha
    -0.08
     vider
    -0.08
     presenter
    -0.08
    arian
    -0.08
     Gewinner
    -0.08
     charakter
    -0.08
     characterized
    -0.08
     constructive
    -0.08
    POSITIVE LOGITS
     conversions
    0.11
     units
    0.11
    单位
    0.10
     Units
    0.10
    Conversions
    0.10
     unit
    0.10
    	unit
    0.09
     unidades
    0.09
     pulgadas
    0.09
    units
    0.09
    Activations Density 0.039%

    No Known Activations