© 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. 97258
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
     wote
    -0.09
    ће
    -0.08
    avase
    -0.08
    વાથી
    -0.08
     Ва
    -0.08
    লে
    -0.08
     Monument
    -0.08
     ಸಾವ
    -0.08
    ’ল
    -0.07
     cayó
    -0.07
    POSITIVE LOGITS
    одейств
    0.18
    owanie
    0.09
    handlungen
    0.08
    ост
    0.08
    spannung
    0.08
    wirkung
    0.08
    од
    0.08
    ്ദ
    0.08
    aktion
    0.08
    нич
    0.08
    Activations Density 0.001%

    No Known Activations