© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64687
    Prev
    Next
    INDEX
    Explanations

    themselves

    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
    ines
    -0.08
     manera
    -0.08
     domin
    -0.08
    with
    -0.08
     performs
    -0.07
     peaks
    -0.07
    INE
    -0.07
    (section
    -0.07
    opes
    -0.07
    ઘ
    -0.07
    POSITIVE LOGITS
     restante
    0.12
    Remaining
    0.11
     बाकी
    0.11
     Remaining
    0.11
     pozost
    0.11
     остается
    0.11
     verble
    0.11
     remaining
    0.11
     ಉಳ
    0.10
    remaining
    0.10
    Activations Density 0.072%

    No Known Activations