© 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. 236
    Prev
    Next
    INDEX
    Explanations

    is

    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
     Beige
    -0.09
     besch
    -0.08
     widers
    -0.08
     palettes
    -0.08
     beige
    -0.08
     �
    -0.08
    一定
    -0.07
     menj
    -0.07
     besteht
    -0.07
     änd
    -0.07
    POSITIVE LOGITS
    iciar
    0.08
     הפר
    0.07
     �
    0.07
     ministers
    0.07
    cri
    0.07
     страхов
    0.07
     cov
    0.07
     cooperating
    0.07
    criber
    0.07
    icia
    0.07
    Activations Density 0.054%

    No Known Activations