© 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. 26532
    Prev
    Next
    INDEX
    Explanations

    oche

    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
     gecon
    -0.08
    ադր
    -0.08
    adha
    -0.08
     Bida
    -0.08
    )+
    -0.08
    gevoegd
    -0.08
     électronique
    -0.08
     papar
    -0.08
     documental
    -0.07
     身
    -0.07
    POSITIVE LOGITS
     buns
    0.09
     refers
    0.08
     peri
    0.08
    .springframework
    0.08
     communicates
    0.08
     ניס
    0.08
    .fasterxml
    0.08
     referring
    0.07
    .sam
    0.07
    peri
    0.07
    Activations Density 0.005%

    No Known Activations