© 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. 50628
    Prev
    Next
    INDEX
    Explanations

    Forced

    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
    Ob
    -0.09
     Ob
    -0.09
     ob
    -0.09
    ob
    -0.08
     obstruction
    -0.08
    -0.08
    .ob
    -0.08
     Obst
    -0.08
    _ob
    -0.08
     integrates
    -0.07
    POSITIVE LOGITS
    уд
    0.11
    ужден
    0.10
    _FORCE
    0.09
    .force
    0.09
    wongen
    0.09
     hack
    0.09
     forced
    0.09
     devil
    0.08
    .about
    0.08
     fuerza
    0.08
    Activations Density 0.001%
    No Known Activations