© 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. 71123
    Prev
    Next
    INDEX
    Explanations

    haven't

    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
    _clause
    -0.08
    Clause
    -0.08
     Soll
    -0.08
     ci
    -0.08
     prim
    -0.08
     Geno
    -0.08
    ောင်း
    -0.07
     Should
    -0.07
     beurre
    -0.07
     Stacey
    -0.07
    POSITIVE LOGITS
    以来
    0.09
    多久
    0.09
    同期
    0.09
     tentu
    0.09
     اتصال
    0.08
    几年
    0.08
     yet
    0.08
     నుం�
    0.08
     longtemps
    0.08
     থেকেই
    0.08
    Activations Density 0.032%

    No Known Activations