© 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. 23-RESID-POST-AA
    11. 48221
    Prev
    Next
    INDEX
    Explanations

    д

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lograr
    -0.09
     بهره
    -0.08
     proxies
    -0.08
     achieve
    -0.08
    ’d
    -0.08
     definir
    -0.08
     במח
    -0.07
     datasource
    -0.07
    ذ
    -0.07
    eqert
    -0.07
    POSITIVE LOGITS
    ані
    0.10
    ось
    0.08
    ане
    0.08
    anus
    0.08
    анные
    0.08
     complexity
    0.08
    АН
    0.07
    анного
    0.07
     trình
    0.07
    ОД
    0.07
    Activations Density 0.001%

    No Known Activations