© 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. 3-RESID-POST-AA
    11. 2520
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tama
    -0.08
     �
    -0.07
    စ
    -0.07
     mambo
    -0.07
     hinzu
    -0.07
    Pred
    -0.07
     Canon
    -0.07
    把
    -0.07
    ุง
    -0.07
    .params
    -0.07
    POSITIVE LOGITS
     ज्य
    0.08
    ledes
    0.08
     nutshell
    0.08
    anu
    0.08
     Sama
    0.07
    附近
    0.07
    -même
    0.07
     footing
    0.07
    时候
    0.07
     extrad
    0.07
    Activations Density 0.002%

    No Known Activations