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. 48973
    Prev
    Next
    INDEX
    Explanations

    eds

    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
     filtering
    -0.08
    Gray
    -0.08
     ramp
    -0.08
     eup
    -0.08
    abouts
    -0.08
     भूम
    -0.07
     succumb
    -0.07
    _GRAY
    -0.07
     enter
    -0.07
     prow
    -0.07
    POSITIVE LOGITS
    독
    0.08
     Clayton
    0.08
     CL
    0.08
     heta
    0.08
     cljs
    0.07
    �
    0.07
    agli
    0.07
     ধরে
    0.07
    II
    0.07
    ...↵↵↵↵
    0.07
    Activations Density 0.283%

    No Known Activations