© 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. 48184
    Prev
    Next
    INDEX
    Explanations

    Calculations

    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
     svo
    -0.08
    hob
    -0.08
    ionais
    -0.08
    ifiziert
    -0.08
     Gebrauch
    -0.07
     rhoi
    -0.07
    rið
    -0.07
     livres
    -0.07
     koti
    -0.07
    ILING
    -0.07
    POSITIVE LOGITS
     nearly
    0.10
    0.08
    -ne
    0.07
     Face
    0.07
    GEST
    0.07
    SE
    0.07
     almost
    0.07
    แข
    0.07
     Mater
    0.07
    谢谢
    0.07
    Activations Density 0.103%
    No Known Activations