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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11677
    Prev
    Next
    INDEX
    Explanations

    vision

    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
    Exclusive
    -0.10
    Notes
    -0.09
    Personnel
    -0.09
     Exclusive
    -0.09
    Mal
    -0.08
     Notes
    -0.08
     Personnel
    -0.08
     notes
    -0.08
     personnel
    -0.08
     Mal
    -0.08
    POSITIVE LOGITS
     zorgt
    0.07
     cup
    0.07
    .cd
    0.07
    配
    0.07
     eint
    0.07
     позиции
    0.07
    LCD
    0.07
    。”↵↵
    0.07
     配
    0.07
     cd
    0.07
    Activations Density 0.000%

    No Known Activations