© 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. 609
    Prev
    Next
    INDEX
    Explanations

    dark mode

    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
     sincere
    -0.08
    yards
    -0.08
     errs
    -0.08
     lined
    -0.08
    numer
    -0.08
     precisa
    -0.07
     disappoint
    -0.07
     singles
    -0.07
    116
    -0.07
     yards
    -0.07
    POSITIVE LOGITS
    Toggle
    0.17
     переключ
    0.16
     toggle
    0.15
     Toggle
    0.15
     togg
    0.14
    .toggle
    0.14
    _toggle
    0.14
    Switcher
    0.14
    toggle
    0.14
    .switch
    0.13
    Activations Density 0.006%

    No Known Activations