© 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. 70299
    Prev
    Next
    INDEX
    Explanations

    chemical equilibrium

    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
    caster
    -0.08
     Logan
    -0.08
     UM
    -0.08
     Maine
    -0.07
    .inverse
    -0.07
    खी
    -0.07
    ريمة
    -0.07
     mí
    -0.07
     indis
    -0.07
     renaissance
    -0.07
    POSITIVE LOGITS
     अवस्था
    0.09
    泊
    0.09
    状態
    0.08
     whereby
    0.08
     poin
    0.07
    状态
    0.07
    住
    0.07
    Disc
    0.07
     Epstein
    0.07
     làm
    0.07
    Activations Density 0.005%

    No Known Activations