© 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. 99359
    Prev
    Next
    INDEX
    Explanations

    adsorption

    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
    शनल
    -0.08
     dodge
    -0.08
     kindness
    -0.08
     Workbook
    -0.08
     Abigail
    -0.08
    embo
    -0.08
     Obl
    -0.08
     executivo
    -0.08
    慈
    -0.08
     flair
    -0.07
    POSITIVE LOGITS
    Ads
    0.14
     adsorption
    0.14
     Ads
    0.12
     ads
    0.11
     guests
    0.11
    _ads
    0.11
    Guests
    0.11
     onto
    0.10
    Guest
    0.10
     guest
    0.10
    Activations Density 0.006%

    No Known Activations