© 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. 79300
    Prev
    Next
    INDEX
    Explanations

    possibly

    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
     allegedly
    -0.09
     reportedly
    -0.09
     aparentemente
    -0.09
     apparently
    -0.08
     seemingly
    -0.08
    vela
    -0.08
     presumably
    -0.08
    =row
    -0.07
    npm
    -0.07
     evidently
    -0.07
    POSITIVE LOGITS
    mals
    0.09
    因为
    0.09
     Yin
    0.09
     לכך
    0.08
    तः
    0.08
     לכל
    0.08
     easiest
    0.08
     intentional
    0.08
     أنك
    0.07
     कि
    0.07
    Activations Density 0.021%

    No Known Activations