© 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. 26585
    Prev
    Next
    INDEX
    Explanations

    Finance and banking

    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
     Localization
    -0.08
     preceded
    -0.08
    anek
    -0.08
     preced
    -0.08
     rescue
    -0.08
    नाक
    -0.07
     Rescue
    -0.07
     Ritual
    -0.07
     authent
    -0.07
    ेस
    -0.07
    POSITIVE LOGITS
     investments
    0.13
     money
    0.12
     rente
    0.11
     العملات
    0.11
     faiz
    0.11
     rendement
    0.11
     juros
    0.11
     ETFs
    0.11
    赚钱
    0.10
     stipend
    0.10
    Activations Density 0.036%

    No Known Activations