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. 9156
    Prev
    Next
    INDEX
    Explanations

    unreal

    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
    (fp
    -0.08
     steward
    -0.08
     Cil
    -0.08
    FP
    -0.08
    GPIO
    -0.08
     заявление
    -0.08
    一句
    -0.08
     fluores
    -0.08
     szyb
    -0.08
    Stamped
    -0.08
    POSITIVE LOGITS
    ults
    0.07
     shady
    0.07
     условий
    0.07
     fantast
    0.07
     Diff
    0.07
     compute
    0.07
     uh
    0.07
     architectures
    0.07
    arke
    0.07
     halluc
    0.07
    Activations Density 0.003%

    No Known Activations