© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95635
    Prev
    Next
    INDEX
    Explanations

    |

    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
    <'
    -0.09
    ban
    -0.08
     випад
    -0.08
     approximately
    -0.07
     склад
    -0.07
     відк
    -0.07
    .Substring
    -0.07
     تقريب
    -0.07
     ọzọ
    -0.07
     imposing
    -0.07
    POSITIVE LOGITS
     Poor
    0.08
     Chem
    0.08
    emark
    0.08
    Subviews
    0.08
     kaliteli
    0.08
     HOURS
    0.08
     Vin
    0.08
     Behavioral
    0.08
    Chem
    0.08
    otin
    0.08
    Activations Density 0.005%

    No Known Activations