Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90087
    Prev
    Next
    INDEX
    Explanations

    technical/academic texts

    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
     stesso
    -0.08
     boiled
    -0.08
    گران
    -0.08
     الاست
    -0.08
     çalışmalar
    -0.08
    larından
    -0.08
    است
    -0.08
     anw
    -0.07
    zeiten
    -0.07
    gruppen
    -0.07
    POSITIVE LOGITS
     quelcon
    0.09
     horses
    0.09
    名
    0.09
     ambul
    0.08
     cualquiera
    0.08
     fenced
    0.08
     perfectly
    0.08
     variety
    0.08
     sinun
    0.07
     hiv
    0.07
    Activations Density 3.171%

    No Known Activations