© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8044
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Já
    -0.08
    &t
    -0.08
    /profile
    -0.07
    ¿
    -0.07
     chiefly
    -0.07
    /m
    -0.07
     spal
    -0.07
    ½
    -0.07
    enced
    -0.07
     flotation
    -0.07
    POSITIVE LOGITS
     tini
    0.08
     Euros
    0.08
     duct
    0.08
     Bikini
    0.08
     Bree
    0.08
     obl
    0.08
     Lego
    0.08
     Pip
    0.08
    kia
    0.08
     diket
    0.08
    Activations Density 0.001%

    No Known Activations