© 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. 23-RESID-POST-AA
    11. 51834
    Prev
    Next
    INDEX
    Explanations

    Technical Documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ozone
    -0.08
    ec
    -0.07
    ני
    -0.07
    Ul
    -0.07
     sentido
    -0.07
    ना
    -0.07
    setq
    -0.07
    iaz
    -0.07
     oc
    -0.07
     shattered
    -0.06
    POSITIVE LOGITS
    ំហ
    0.09
    weng
    0.09
    wander
    0.09
     связанных
    0.08
    _src
    0.08
    beans
    0.08
    /antlr
    0.08
    'emb
    0.08
     Xamarin
    0.08
     Src
    0.08
    Activations Density 0.001%

    No Known Activations