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. 46300
    Prev
    Next
    INDEX
    Explanations

    slower

    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
    allergenic
    -0.08
    外
    -0.07
    inject
    -0.07
    ilig
    -0.07
    alia
    -0.07
    arin
    -0.07
    али
    -0.07
    aurant
    -0.07
     외
    -0.07
    .Temp
    -0.07
    POSITIVE LOGITS
     slower
    0.11
     quieter
    0.09
    <R
    0.08
     sluggish
    0.08
    -ray
    0.08
    (pow
    0.08
     slow
    0.08
     offline
    0.08
     rz
    0.08
     calmer
    0.08
    Activations Density 0.363%

    No Known Activations