© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44945
    Prev
    Next
    INDEX
    Explanations

    inflater

    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
     kamp
    -0.08
     концентра
    -0.08
    -status
    -0.08
    уст
    -0.08
    forum
    -0.08
    grep
    -0.08
     Status
    -0.08
     grep
    -0.08
     forum
    -0.07
    त्न
    -0.07
    POSITIVE LOGITS
     inflater
    0.13
    .inflate
    0.12
    (inflater
    0.11
    /render
    0.11
    inflate
    0.10
    Inflater
    0.09
     Inflate
    0.08
     inflate
    0.08
     Coaches
    0.08
    /template
    0.08
    Activations Density 0.001%

    No Known Activations