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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129222
    Prev
    Next
    INDEX
    Explanations

    Enable annotations

    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
     urn
    -0.09
     ethically
    -0.08
     Adobe
    -0.08
    088
    -0.08
    841
    -0.08
     ώ
    -0.08
     hypo
    -0.08
    894
    -0.08
     दूस
    -0.07
    _COST
    -0.07
    POSITIVE LOGITS
    @Configuration
    0.12
    @Enable
    0.10
     automatically
    0.09
     reconhe
    0.08
     aner
    0.08
     선언
    0.08
    akad
    0.07
     autod
    0.07
     initialization
    0.07
    (loader
    0.07
    Activations Density 0.003%

    No Known Activations