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. 90936
    Prev
    Next
    INDEX
    Explanations

    modern

    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
    arle
    -0.07
     espac
    -0.07
    Reusable
    -0.07
    recv
    -0.07
     atop
    -0.07
     али
    -0.07
    -use
    -0.07
     oversees
    -0.07
    chez
    -0.07
     }
    ↵
    -0.07
    POSITIVE LOGITS
     siècle
    0.08
     atrocities
    0.08
    -era
    0.08
     nations
    0.08
     enlightenment
    0.08
    忽
    0.08
     Protestant
    0.08
     konsep
    0.08
     begynd
    0.07
    ökk
    0.07
    Activations Density 0.011%

    No Known Activations