© 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. 112573
    Prev
    Next
    INDEX
    Explanations

    auch

    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
    two
    -0.08
    SMART
    -0.08
    smarty
    -0.08
    more
    -0.07
    boost
    -0.07
     SATA
    -0.07
    双方
    -0.07
     SMART
    -0.07
    ब्ल
    -0.07
     marqué
    -0.07
    POSITIVE LOGITS
    .Tele
    0.08
     الاب
    0.08
     Acid
    0.08
     alkal
    0.08
     વિષ
    0.07
     Illegal
    0.07
     deport
    0.07
     inhab
    0.07
     Detox
    0.07
     தவ
    0.07
    Activations Density 0.005%

    No Known Activations