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. 3-RESID-POST-AA
    6. 1834
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arab
    -0.08
     combinaison
    -0.08
    OV
    -0.08
     résidence
    -0.08
     pré
    -0.08
     olt
    -0.07
    oud
    -0.07
     cita
    -0.07
     Membership
    -0.07
    19
    -0.07
    POSITIVE LOGITS
    croll
    0.08
    పు
    0.08
     Dar
    0.07
     дает
    0.07
    剧
    0.07
    sg
    0.07
    劇
    0.07
    ী
    0.07
     Redux
    0.07
     sickness
    0.07
    Activations Density 0.007%

    No Known Activations