Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98588
    Prev
    Next
    INDEX
    Explanations

    -b

    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
     piernas
    -0.08
     gyfl
    -0.08
    SETS
    -0.08
     arbejds
    -0.07
    ETS
    -0.07
    нями
    -0.07
    চিত
    -0.07
     fencing
    -0.07
     Covers
    -0.07
     pilares
    -0.07
    POSITIVE LOGITS
    ott
    0.13
    ாட்ட
    0.10
    ാട്ട
    0.09
    ോട്ട
    0.09
    ಾಟ
    0.09
    OTT
    0.08
    ॉट
    0.08
    ottle
    0.08
    ট
    0.08
    otto
    0.08
    Activations Density 0.000%

    No Known Activations