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. 9033
    Prev
    Next
    INDEX
    Explanations

    overlooking

    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
     born
    -0.08
    ون
    -0.08
    वेयर
    -0.08
     पहन
    -0.07
     ಪದ
    -0.07
     Flyers
    -0.07
     స్థ
    -0.07
     соглаш
    -0.07
     wavelengths
    -0.07
    件
    -0.07
    POSITIVE LOGITS
     vats
    0.09
     MUT
    0.08
     crossroads
    0.08
     mutated
    0.08
     troops
    0.08
     harbour
    0.08
     gardens
    0.08
    kaar
    0.08
     காட்ட
    0.08
     countryside
    0.08
    Activations Density 0.008%

    No Known Activations