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. 102958
    Prev
    Next
    INDEX
    Explanations

    layers

    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
     Spain
    -0.08
     eastern
    -0.07
     Corn
    -0.07
     ^
    -0.07
    575
    -0.07
     Klassiker
    -0.07
    icule
    -0.07
     Lear
    -0.07
    spender
    -0.07
     corn
    -0.07
    POSITIVE LOGITS
    (Dense
    0.09
    Datatype
    0.08
     jooksul
    0.08
     judi
    0.08
     graduation
    0.08
     honden
    0.08
     sequencing
    0.08
    ંપની
    0.07
    ريض
    0.07
     modelling
    0.07
    Activations Density 0.002%

    No Known Activations