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. 65392
    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
     holog
    -0.08
     penchant
    -0.07
     shortages
    -0.07
    aler
    -0.07
     soggior
    -0.07
     bustling
    -0.07
    纠
    -0.07
    langen
    -0.07
     envolvendo
    -0.07
    Lis
    -0.07
    POSITIVE LOGITS
     نسبة
    0.08
     Richter
    0.08
     atributo
    0.08
     "("
    0.08
    חת
    0.08
     hardcore
    0.08
     hierin
    0.08
     numerical
    0.08
     Upr
    0.07
    liner
    0.07
    Activations Density 0.017%

    No Known Activations