© 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. 44825
    Prev
    Next
    INDEX
    Explanations

    line

    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
     hadiah
    -0.08
     жен
    -0.08
     offspring
    -0.08
     multic
    -0.08
     months
    -0.08
     aks
    -0.08
     gg
    -0.08
     gon
    -0.07
     выг
    -0.07
     month
    -0.07
    POSITIVE LOGITS
     lignes
    0.11
     строки
    0.11
    _lines
    0.11
     linhas
    0.11
    .lines
    0.11
    .readline
    0.11
    (lines
    0.11
     Lines
    0.11
    	lines
    0.11
    .Trim
    0.10
    Activations Density 0.010%

    No Known Activations