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. 113991
    Prev
    Next
    INDEX
    Explanations

    Ram

    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
     malo
    -0.10
     tbl
    -0.09
     triv
    -0.09
     qry
    -0.08
     bubb
    -0.08
    ♪
    -0.08
    inch
    -0.08
    ivity
    -0.08
    ุ้น
    -0.08
     мала
    -0.08
    POSITIVE LOGITS
     verse
    0.08
     overt
    0.07
    ायण
    0.07
    ieux
    0.07
     Civil
    0.07
    aih
    0.07
    works
    0.07
     inn
    0.07
     fondamentale
    0.07
     విధ
    0.07
    Activations Density 0.005%

    No Known Activations