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. 61150
    Prev
    Next
    INDEX
    Explanations

    equations

    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
    armat
    -0.08
     lame
    -0.08
     resemblance
    -0.07
     accidental
    -0.07
     youn
    -0.07
     देखने
    -0.07
     counterfeit
    -0.07
     regal
    -0.07
    ало
    -0.07
     संस्करण
    -0.07
    POSITIVE LOGITS
     enters
    0.08
     contributes
    0.08
     vấn
    0.08
    $mail
    0.07
     tár
    0.07
    ="",
    0.07
    Ingrese
    0.07
     Tah
    0.07
     compens
    0.07
     Gh
    0.07
    Activations Density 0.045%

    No Known Activations