© 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. 68136
    Prev
    Next
    INDEX
    Explanations

    single quote

    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
     εξ
    -0.08
     scr
    -0.08
     ew
    -0.07
    aila
    -0.07
     fel
    -0.07
     coarse
    -0.07
    amay
    -0.07
     mě
    -0.07
     Flor
    -0.07
     interf
    -0.07
    POSITIVE LOGITS
     tils
    0.09
     capítulos
    0.08
     prisoners
    0.08
     jub
    0.08
     chapters
    0.08
    ников
    0.07
    暂停
    0.07
     Lennon
    0.07
     dão
    0.07
     gonna
    0.07
    Activations Density 0.001%

    No Known Activations