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. 120191
    Prev
    Next
    INDEX
    Explanations

    gardening

    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
     разд
    -0.10
     Fighter
    -0.08
    ovski
    -0.08
    ुनिक
    -0.08
    undant
    -0.07
     navegar
    -0.07
    exec
    -0.07
     médicos
    -0.07
     metri
    -0.07
     binaries
    -0.07
    POSITIVE LOGITS
     gardening
    0.14
     novice
    0.12
     Gardening
    0.12
     gardeners
    0.12
     novices
    0.12
     gardener
    0.10
     jardin
    0.10
     hortic
    0.10
     beginners
    0.10
     jard
    0.10
    Activations Density 0.018%

    No Known Activations