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. 11822
    Prev
    Next
    INDEX
    Explanations

    Cleaning and conditioning materials

    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
    _cap
    -0.08
    _arr
    -0.08
    .semantic
    -0.08
    _variable
    -0.08
    vant
    -0.08
    omething
    -0.07
    variable
    -0.07
    (variable
    -0.07
    _social
    -0.07
    unique
    -0.07
    POSITIVE LOGITS
    润
    0.10
     तेल
    0.10
     onderhouden
    0.09
     onderhoud
    0.09
     huile
    0.09
     moistur
    0.09
     Conditioner
    0.09
     bakım
    0.09
     grease
    0.09
     THC
    0.09
    Activations Density 0.032%

    No Known Activations