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. 112926
    Prev
    Next
    INDEX
    Explanations

    linked

    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
    errar
    -0.08
    ertal
    -0.08
    ichannel
    -0.08
    ert
    -0.08
    decken
    -0.08
     Arbeitgeber
    -0.08
    plac
    -0.08
     Claudia
    -0.07
     Einst
    -0.07
    र्त
    -0.07
    POSITIVE LOGITS
     rope
    0.09
    方便
    0.09
    尾
    0.09
     shrub
    0.09
     woes
    0.09
    Advantages
    0.08
     Rope
    0.08
    bahn
    0.08
     Advantages
    0.08
     Fibonacci
    0.08
    Activations Density 0.003%

    No Known Activations