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. 23765
    Prev
    Next
    INDEX
    Explanations

    CFD simulations

    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
     Tinder
    -0.11
     tumblr
    -0.09
    (tweet
    -0.09
     bracelet
    -0.09
     bracelets
    -0.09
     Craigslist
    -0.09
     scammers
    -0.09
    _album
    -0.09
     tweet
    -0.09
    .twitter
    -0.09
    POSITIVE LOGITS
     scalar
    0.11
    scalar
    0.10
     Scalar
    0.10
    Scalar
    0.10
    -fluid
    0.10
     convection
    0.10
    vtk
    0.09
     Helm
    0.09
     Fluent
    0.09
     inlet
    0.09
    Activations Density 0.009%

    No Known Activations