© 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. 64812
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts

    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
    तम
    -0.08
     prescription
    -0.07
    ugia
    -0.07
    -smart
    -0.07
     thee
    -0.07
    inv
    -0.07
    -mode
    -0.07
     Déc
    -0.06
     necessarily
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Schön
    0.08
     sharply
    0.08
    ，因此
    0.08
     Mare
    0.08
     хад
    0.07
     centred
    0.07
    .estado
    0.07
     가운데
    0.07
     geweest
    0.07
    ritten
    0.07
    Activations Density 0.085%

    No Known Activations