© 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. 108617
    Prev
    Next
    INDEX
    Explanations

    projects and ideas

    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
     frecuentes
    -0.09
     persec
    -0.09
     unsett
    -0.08
     encuentros
    -0.08
     conversaciones
    -0.08
     isla
    -0.08
     Piso
    -0.08
     regimes
    -0.08
     Gespr
    -0.08
    Mt
    -0.08
    POSITIVE LOGITS
     submitted
    0.12
     제출
    0.12
     submission
    0.12
     originality
    0.12
    作品
    0.11
    submitted
    0.11
     submissions
    0.10
     उन्होंने
    0.10
    Submitted
    0.10
     Submission
    0.10
    Activations Density 0.071%

    No Known Activations