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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68847
    Prev
    Next
    INDEX
    Explanations

    ac

    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
     různ
    -0.08
     nauw
    -0.08
     confidential
    -0.08
     hobbies
    -0.08
     attitudes
    -0.08
    ického
    -0.08
     opiskel
    -0.08
    anjang
    -0.08
     ASK
    -0.08
     workings
    -0.08
    POSITIVE LOGITS
    Fim
    0.08
     Gregory
    0.08
     वो
    0.08
     freeway
    0.07
    Elt
    0.07
    ")),↵
    0.07
     বাধ
    0.07
     препят
    0.07
     वाले
    0.07
    障
    0.07
    Activations Density 0.000%

    No Known Activations