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. 48581
    Prev
    Next
    INDEX
    Explanations

    purpose

    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
     Lydia
    -0.08
     Mario
    -0.07
     Stuff
    -0.07
    rant
    -0.07
     Alors
    -0.07
     पाए
    -0.07
     demikian
    -0.07
     avanzado
    -0.07
    -And
    -0.07
     Madden
    -0.07
    POSITIVE LOGITS
     desired
    0.12
     원하는
    0.12
    desired
    0.12
     gewenste
    0.10
    Quieres
    0.10
    Desired
    0.10
     muốn
    0.10
     chcete
    0.09
     deseas
    0.09
     хотите
    0.09
    Activations Density 0.082%

    No Known Activations