© 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. 3-RESID-POST-AA
    11. 2691
    Prev
    Next
    INDEX
    Explanations

    record

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wi
    -0.08
     Single
    -0.08
     بالق
    -0.07
    පා
    -0.07
    пе
    -0.07
     Bert
    -0.07
     Pastor
    -0.07
     Bravo
    -0.07
    136
    -0.07
     goo
    -0.07
    POSITIVE LOGITS
    録
    0.08
     cohort
    0.08
     utilizing
    0.07
     Yan
    0.07
    �
    0.07
    ND
    0.07
     chrono
    0.07
    িট
    0.07
    iza
    0.07
     য
    0.07
    Activations Density 0.021%

    No Known Activations