© 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. 31112
    Prev
    Next
    INDEX
    Explanations

    virus attachment and receptors

    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
     word
    -0.08
    word
    -0.08
     palabra
    -0.08
    irth
    -0.08
    -word
    -0.08
     audited
    -0.08
     palavra
    -0.08
     grandfather
    -0.07
     শব্দ
    -0.07
     운영
    -0.07
    POSITIVE LOGITS
     docking
    0.14
     adhesion
    0.12
     взаимодейств
    0.11
     matchmaking
    0.11
     adsorption
    0.10
     Adhes
    0.10
     संपर्क
    0.10
     handshake
    0.10
     receptors
    0.10
     контак
    0.10
    Activations Density 0.009%

    No Known Activations