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. 48686
    Prev
    Next
    INDEX
    Explanations

    dry

    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
     kaum
    -0.08
    --------------------------------
    -0.07
     conduit
    -0.07
    નો
    -0.07
     nab
    -0.07
    isang
    -0.07
    ----------------
    -0.07
     Tan
    -0.07
     Derived
    -0.07
     sensory
    -0.07
    POSITIVE LOGITS
    ША
    0.09
     миров
    0.08
    ाध्यक्ष
    0.08
     međunar
    0.08
    票
    0.08
     principe
    0.08
     Premi
    0.08
     голову
    0.08
     छुट
    0.08
    귀
    0.08
    Activations Density 0.000%

    No Known Activations