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. 9048
    Prev
    Next
    INDEX
    Explanations

    excel coding

    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
     dma
    -0.08
     genders
    -0.08
     ponad
    -0.08
     laid
    -0.08
     चार
    -0.08
     gender
    -0.08
     Depp
    -0.08
     rodz
    -0.08
    Four
    -0.08
    gender
    -0.08
    POSITIVE LOGITS
    .Trigger
    0.09
    .Notify
    0.08
    .Alert
    0.08
     কৰিব
    0.08
     atomic
    0.08
    .But
    0.08
    .Time
    0.08
    স্পত
    0.08
    ابه
    0.08
     কৰাৰ
    0.08
    Activations Density 0.005%

    No Known Activations