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. 76494
    Prev
    Next
    INDEX
    Explanations

    on

    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
     stared
    -0.10
     поскольку
    -0.08
    مس
    -0.08
    措
    -0.08
     но
    -0.08
     வர
    -0.07
     sofern
    -0.07
     embodied
    -0.07
    Lleg
    -0.07
    |null
    -0.07
    POSITIVE LOGITS
    -built
    0.09
     iso
    0.09
     Gefühl
    0.08
    ापा
    0.08
    ються
    0.07
    ച്ചു
    0.07
    atenate
    0.07
    shin
    0.07
    -adị
    0.07
     początku
    0.07
    Activations Density 0.027%

    No Known Activations