Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 119328
    Prev
    Next
    INDEX
    Explanations

    new line and coding

    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
     URLWith
    -0.08
     bhe
    -0.08
     Manu
    -0.08
     Juventus
    -0.08
     �
    -0.08
     Kumar
    -0.07
     Parm
    -0.07
     darunter
    -0.07
     Perc
    -0.07
     wat
    -0.07
    POSITIVE LOGITS
    mor
    0.09
    ുകയ
    0.08
    syn
    0.08
    .exit
    0.08
    Stopping
    0.08
     enemigo
    0.08
    ,那么
    0.08
    11
    0.08
    (reset
    0.07
    Notation
    0.07
    Activations Density 0.000%

    No Known Activations