© 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. 48105
    Prev
    Next
    INDEX
    Explanations

    ú

    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
    London
    -0.07
    (Of
    -0.07
    牙
    -0.07
     Dame
    -0.07
    ㆍ
    -0.07
     Chicago
    -0.07
    -New
    -0.07
    ANI
    -0.07
    Chicago
    -0.07
     zao
    -0.07
    POSITIVE LOGITS
     gond
    0.09
     snorkeling
    0.09
    考虑
    0.08
     relève
    0.08
     revise
    0.08
    estors
    0.08
    .mkdirs
    0.08
     piscine
    0.08
     Prefix
    0.08
     underwater
    0.08
    Activations Density 0.000%

    No Known Activations