© 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. 75667
    Prev
    Next
    INDEX
    Explanations

    path/location

    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
     tann
    -0.07
     aplic
    -0.07
    geber
    -0.07
    (argc
    -0.07
     binnen
    -0.07
    ast
    -0.07
    ne
    -0.07
     eingeb
    -0.06
     Parameters
    -0.06
    ident
    -0.06
    POSITIVE LOGITS
    Preferred
    0.09
     préfér
    0.09
    Ụ
    0.09
     prefere
    0.09
     préférence
    0.09
     preferably
    0.09
     cds
    0.09
     любит
    0.08
     terci
    0.08
    Heavy
    0.08
    Activations Density 0.008%

    No Known Activations