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

    Neuronpedia

    Jacobian LensNEW
    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. 69122
    Prev
    Next
    INDEX
    Explanations

    street locations

    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
    	prev
    -0.08
     शाख
    -0.08
    गीत
    -0.08
    स्
    -0.08
     branch
    -0.08
     qualified
    -0.08
     ổ
    -0.08
     Qo
    -0.08
    uentes
    -0.07
    枝
    -0.07
    POSITIVE LOGITS
     bustling
    0.09
     glitter
    0.08
     곳
    0.08
    Adjacent
    0.08
     Aula
    0.08
     관광
    0.08
    皇
    0.08
     nightlife
    0.08
    之后
    0.08
     אחרי
    0.08
    Activations Density 0.028%

    No Known Activations