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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 53094
    Prev
    Next
    INDEX
    Explanations

    text

    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
     comodidad
    -0.07
     rozs
    -0.07
    赋
    -0.07
     vid
    -0.07
     piac
    -0.07
     pati
    -0.07
     Visitor
    -0.07
     Challenger
    -0.07
    雕
    -0.07
     leggen
    -0.07
    POSITIVE LOGITS
     lykk
    0.08
    })
    0.08
     *)
    0.08
    Probability
    0.08
    heta
    0.08
     حدوث
    0.08
     lyck
    0.08
     probability
    0.07
    ):
    0.07
     blackjack
    0.07
    Activations Density 0.024%

    No Known Activations