© 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. 94879
    Prev
    Next
    INDEX
    Explanations

    code or data

    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
     Levin
    -0.08
    441
    -0.07
    pan
    -0.07
    ofie
    -0.07
    +i
    -0.07
     contributions
    -0.07
    44
    -0.07
     Zou
    -0.07
    pectives
    -0.07
     PTR
    -0.07
    POSITIVE LOGITS
     tect
    0.09
     piedi
    0.08
     jacuzzi
    0.08
     갑
    0.08
     koht
    0.08
     incar
    0.07
     construit
    0.07
     š
    0.07
     bathtub
    0.07
    İN
    0.07
    Activations Density 0.003%

    No Known Activations