© 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. 69831
    Prev
    Next
    INDEX
    Explanations

    stopped

    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
     firm's
    -0.09
     perfiles
    -0.08
    Depth
    -0.08
     perfil
    -0.07
    "profile
    -0.07
    사의
    -0.07
     případě
    -0.07
    Related
    -0.07
    Partial
    -0.07
     philanthrop
    -0.07
    POSITIVE LOGITS
    ไป
    0.08
     каш
    0.08
    碍
    0.08
    句话
    0.08
     locom
    0.08
     WAV
    0.07
    ать
    0.07
    lum
    0.07
     doorway
    0.07
     �
    0.07
    Activations Density 0.001%

    No Known Activations