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. 44211
    Prev
    Next
    INDEX
    Explanations

    module

    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
     adatt
    -0.08
     AD
    -0.08
     OD
    -0.08
     perimeter
    -0.07
     polygon
    -0.07
     adat
    -0.07
     driving
    -0.07
     ol
    -0.07
     Kik
    -0.07
     fencing
    -0.07
    POSITIVE LOGITS
    Lub
    0.10
    [file
    0.10
    NSBundle
    0.09
     Goa
    0.09
    .loaded
    0.09
    @Module
    0.09
    [module
    0.09
     teeb
    0.08
     joué
    0.08
    _finished
    0.08
    Activations Density 0.004%

    No Known Activations