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. 59793
    Prev
    Next
    INDEX
    Explanations

    Articles and "for"

    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
     경쟁
    -0.09
     competitors
    -0.08
    (~
    -0.08
    gradable
    -0.08
    fillable
    -0.07
    iffe
    -0.07
    ™
    -0.07
     competition
    -0.07
     свя
    -0.07
     بشأن
    -0.07
    POSITIVE LOGITS
     printing
    0.16
    打印
    0.15
    Printing
    0.15
     Printing
    0.14
    .Print
    0.14
    .print
    0.14
     prints
    0.14
     imprimir
    0.14
     Print
    0.13
    Print
    0.13
    Activations Density 0.016%

    No Known Activations