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. 11872
    Prev
    Next
    INDEX
    Explanations

    the

    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
     перед
    -0.07
     COMP
    -0.07
    AMB
    -0.07
     nah
    -0.07
     рекоменд
    -0.07
     am
    -0.06
     erhält
    -0.06
    016
    -0.06
    본
    -0.06
     తయ
    -0.06
    POSITIVE LOGITS
     picturesque
    0.09
     villagers
    0.09
     gelo
    0.09
     newfound
    0.09
    -vars
    0.08
     outskirts
    0.08
     गांव
    0.08
     मंत्रालय
    0.08
     besmet
    0.08
     Ontario
    0.08
    Activations Density 0.026%

    No Known Activations