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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70519
    Prev
    Next
    INDEX
    Explanations

    reacts

    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
    ossi
    -0.09
    Entry
    -0.08
    Interface
    -0.08
     entrants
    -0.08
    uentes
    -0.07
    Enterprise
    -0.07
     institutions
    -0.07
    ift
    -0.07
    Dette
    -0.07
    Hoi
    -0.07
    POSITIVE LOGITS
     Natural
    0.09
    -natural
    0.08
    _inline
    0.08
     प्राकृतिक
    0.08
     Stable
    0.08
    ುದ
    0.08
    weighted
    0.08
    natural
    0.07
    ടുത്ത
    0.07
    stable
    0.07
    Activations Density 0.000%

    No Known Activations