© 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. 24725
    Prev
    Next
    INDEX
    Explanations

    academic paper citations

    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
     armed
    -0.10
     ↓
    -0.08
     विभ
    -0.08
     Clint
    -0.07
     Cay
    -0.07
     erhö
    -0.07
     Amp
    -0.07
     naturalmente
    -0.07
     Ganze
    -0.07
     Tops
    -0.07
    POSITIVE LOGITS
    doi
    0.10
     daad
    0.08
     Scholar
    0.08
     DOI
    0.08
     Symposium
    0.07
    zaak
    0.07
    ுடைய
    0.07
    alakkersuis
    0.07
    adzira
    0.07
    asib
    0.07
    Activations Density 0.002%

    No Known Activations