© 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. 6168
    Prev
    Next
    INDEX
    Explanations

    Hy

    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
     Finest
    -0.08
    اشت
    -0.07
    	of
    -0.07
     irgendwie
    -0.07
    -0.07
    #if
    -0.07
    either
    -0.07
    aviest
    -0.07
    מיט
    -0.07
     clog
    -0.07
    POSITIVE LOGITS
    aluronic
    0.17
    pertension
    0.16
    giène
    0.15
    derabad
    0.15
     vọng
    0.13
    gië
    0.12
    strix
    0.12
    undai
    0.11
    pert
    0.11
    acin
    0.10
    Activations Density 0.004%
    No Known Activations