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. 112079
    Prev
    Next
    INDEX
    Explanations

    smallest

    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
     фрукт
    -0.08
    aped
    -0.08
     fungus
    -0.08
     стран
    -0.08
     climbs
    -0.08
     служ
    -0.08
     bodybuilding
    -0.08
     staple
    -0.08
    나
    -0.08
     речи
    -0.08
    POSITIVE LOGITS
    aza
    0.08
    az
    0.08
     Lam
    0.08
     hypers
    0.07
    Lam
    0.07
     \$
    0.07
     esit
    0.07
     Elliott
    0.07
    155
    0.07
     τρόπο
    0.07
    Activations Density 0.014%

    No Known Activations