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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 75371
    Prev
    Next
    INDEX
    Explanations

    file systems and code

    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
     dubb
    -0.09
     periodistas
    -0.08
     NATO
    -0.08
    -lein
    -0.08
    cano
    -0.07
     Matrix
    -0.07
     nazw
    -0.07
     professionalism
    -0.07
    ाभ
    -0.07
     teatral
    -0.07
    POSITIVE LOGITS
     শুক
    0.09
     overflowing
    0.09
     genügend
    0.09
    磁
    0.09
     soil
    0.08
    พื้นที่
    0.08
     plentiful
    0.08
     ample
    0.08
     पर्याप्त
    0.08
     abundant
    0.08
    Activations Density 0.009%

    No Known Activations