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. 112792
    Prev
    Next
    INDEX
    Explanations

    software transactions and configurations

    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
    CMS
    -0.08
    Meet
    -0.08
    ет
    -0.08
     യോഗ
    -0.07
     검사
    -0.07
    ();"
    -0.07
    ();
    -0.07
    ()
    -0.07
    reader
    -0.07
    epụta
    -0.07
    POSITIVE LOGITS
     familiares
    0.08
     tratar
    0.08
     jogar
    0.08
     condição
    0.08
     embl
    0.08
     hér
    0.08
     weißen
    0.07
     pestic
    0.07
     witte
    0.07
    Cpf
    0.07
    Activations Density 0.000%

    No Known Activations