© 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 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. 68893
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    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
     mechanism
    -0.09
     ladder
    -0.08
     emails
    -0.08
    (:,
    -0.07
     seldom
    -0.07
    ете
    -0.07
     Ladder
    -0.07
    ải
    -0.07
     hurricane
    -0.07
     breathing
    -0.07
    POSITIVE LOGITS
    izioni
    0.08
     überzeugt
    0.08
     Curve
    0.08
    izde
    0.07
     abbiamo
    0.07
    ativité
    0.07
     disputes
    0.07
     mēs
    0.07
     diskut
    0.07
     موږ
    0.07
    Activations Density 0.002%

    No Known Activations