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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23422
    Prev
    Next
    INDEX
    Explanations

    excuse reason

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dollar
    -0.08
    मी
    -0.08
    -0.08
    र्ज
    -0.07
     scegli
    -0.07
    से
    -0.07
    िरे
    -0.07
    രും
    -0.07
    fold
    -0.07
     mõned
    -0.07
    POSITIVE LOGITS
     نیست
    0.09
     خب
    0.09
     עולם
    0.08
    លោក
    0.08
     الإصابة
    0.08
     opravdu
    0.08
     정말
    0.08
     детям
    0.07
    !/
    0.07
     Anjeun
    0.07
    Activations Density 0.000%

    No Known Activations