© 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. 96822
    Prev
    Next
    INDEX
    Explanations

    Esperanto language

    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
     Appalach
    -0.09
     விட்ட
    -0.09
     Dolly
    -0.08
    aal
    -0.08
     Saudi
    -0.08
     Appalachian
    -0.08
    асс
    -0.08
     Sydney
    -0.08
    Saudi
    -0.08
    Turkey
    -0.08
    POSITIVE LOGITS
     	ar
    0.20
     aŭ
    0.19
     	iuj
    0.19
     ankaŭ
    0.19
     laŭ
    0.18
     ĝin
    0.18
     povas
    0.18
     antaŭ
    0.18
     kontraŭ
    0.17
     tiuj
    0.17
    Activations Density 0.002%

    No Known Activations