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. 120444
    Prev
    Next
    INDEX
    Explanations

    Something is coming

    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
    _VM
    -0.08
    legg
    -0.08
    ission
    -0.08
    >>↵↵
    -0.08
    apping
    -0.08
    _Result
    -0.07
    urbed
    -0.07
     murdered
    -0.07
    روح
    -0.07
    _ROUTE
    -0.07
    POSITIVE LOGITS
     nearing
    0.11
     imminent
    0.10
     looming
    0.09
     નજીક
    0.09
     vorbei
    0.09
     immin
    0.09
    提醒
    0.09
     underway
    0.09
     semanal
    0.09
     dold
    0.09
    Activations Density 0.082%

    No Known Activations