© 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. 47932
    Prev
    Next
    INDEX
    Explanations

    processor names

    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
     ಕೋವಿಡ್
    -0.10
     कोविड
    -0.09
     코로나
    -0.09
    COVID
    -0.09
     COVID
    -0.09
    onnas
    -0.09
     കോവിഡ്
    -0.09
    iktok
    -0.09
     Һ
    -0.09
     климат
    -0.09
    POSITIVE LOGITS
    Plug
    0.08
     multit
    0.08
     plug
    0.08
     Experiment
    0.07
     Multimedia
    0.07
     Boot
    0.07
     Plug
    0.07
    DAT
    0.07
    .osgi
    0.07
     Bug
    0.07
    Activations Density 0.099%

    No Known Activations