© 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. 19-RESID-POST-AA
    11. 19041
    Prev
    Next
    INDEX
    Explanations

    bracket

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öll
    -0.08
     uygulan
    -0.08
     erwart
    -0.08
     ajili
    -0.08
     bans
    -0.08
    は禁止
    -0.08
    pieces
    -0.08
    utt
    -0.07
    альное
    -0.07
     means
    -0.07
    POSITIVE LOGITS
    )
    0.10
    ),
    0.09
     },
    0.09
     Nếu
    0.08
     Zeker
    0.08
     특히
    0.08
     Но
    0.08
    icia
    0.08
     //
    0.08
     Особ
    0.08
    Activations Density 0.004%

    No Known Activations