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. 45570
    Prev
    Next
    INDEX
    Explanations

    total

    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
     rég
    -0.08
     ___
    -0.08
     tying
    -0.07
     ભૂ
    -0.07
     AKA
    -0.07
    /Desktop
    -0.07
     tente
    -0.07
    neet
    -0.07
    ield
    -0.07
     attaining
    -0.07
    POSITIVE LOGITS
    കെ
    0.09
     fiery
    0.09
     कुल
    0.08
     contagious
    0.08
    血
    0.07
     അഞ്ച്
    0.07
     ukup
    0.07
     lanz
    0.07
     पाँच
    0.07
     pas
    0.07
    Activations Density 0.028%

    No Known Activations