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. 319
    Prev
    Next
    INDEX
    Explanations

    go

    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
    512
    -0.08
     wn
    -0.08
     Credit
    -0.07
     Central
    -0.07
     الواقع
    -0.07
    Film
    -0.07
    SON
    -0.07
     cavern
    -0.07
    IN
    -0.07
    WB
    -0.07
    POSITIVE LOGITS
    掉
    0.13
    werden
    0.09
     thro
    0.09
    Á
    0.08
    zhi
    0.08
     sprouts
    0.08
    pour
    0.08
     হয়ে
    0.08
     lá
    0.08
     muna
    0.08
    Activations Density 0.006%

    No Known Activations