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. 112028
    Prev
    Next
    INDEX
    Explanations

    lottery

    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
    Like
    -0.08
    Station
    -0.08
    Sharp
    -0.07
    avr
    -0.07
    Unlock
    -0.07
    tig
    -0.07
    _like
    -0.07
    ajax
    -0.07
    Portrait
    -0.07
    av
    -0.07
    POSITIVE LOGITS
     сюжет
    0.08
     प्राथमिक
    0.08
     screened
    0.08
     граф
    0.07
     Corpor
    0.07
     randomized
    0.07
     Okt
    0.07
    .BLUE
    0.07
     conflic
    0.07
    oute
    0.07
    Activations Density 0.001%

    No Known Activations