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

    Neuronpedia

    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. 94380
    Prev
    Next
    INDEX
    Explanations

    Affirmation and confirmation

    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
     herr
    -0.08
     Sich
    -0.08
    Slip
    -0.08
     endure
    -0.08
    �
    -0.08
     jad
    -0.08
    خت
    -0.08
    _eff
    -0.08
    ات
    -0.07
     dude
    -0.07
    POSITIVE LOGITS
     pivotal
    0.08
    come
    0.08
     contingent
    0.08
     عبارة
    0.08
     MSM
    0.08
     essential
    0.08
     mors
    0.07
     ug
    0.07
    sm
    0.07
    metr
    0.07
    Activations Density 0.246%

    No Known Activations