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. 58870
    Prev
    Next
    INDEX
    Explanations

    1

    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
     तरीके
    -0.08
     बनाई
    -0.08
    。でも
    -0.08
     आपकी
    -0.08
     बड़े
    -0.07
     उचित
    -0.07
     उस
    -0.07
    Apparently
    -0.07
     उनके
    -0.07
     बड़ी
    -0.07
    POSITIVE LOGITS
     ****************************************************************
    0.08
     Ambient
    0.08
     Gide
    0.08
     Pilot
    0.08
    &#
    0.08
     ************************
    0.08
     Aviation
    0.07
    -suite
    0.07
     William
    0.07
     ****************************************
    0.07
    Activations Density 0.100%

    No Known Activations