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. 111726
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Essentials
    -0.08
     casual
    -0.08
     podpor
    -0.08
    stattung
    -0.08
     propr
    -0.07
    /#
    -0.07
    -0.07
    િના
    -0.07
    :.
    -0.07
    generation
    -0.07
    POSITIVE LOGITS
     Apply
    0.08
     Override
    0.07
    ices
    0.07
     hadd
    0.07
     Existe
    0.07
     Perm
    0.07
    aval
    0.07
    _callable
    0.07
    轨
    0.07
    eli
    0.07
    Activations Density 0.001%

    No Known Activations