© 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. 7-RESID-POST-AA
    11. 1187
    Prev
    Next
    INDEX
    Explanations

    wildcard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toga
    -0.08
     والاج
    -0.08
     Dior
    -0.08
     cauc
    -0.08
     Vessel
    -0.07
     Lime
    -0.07
     Sign
    -0.07
    .billing
    -0.07
     Rechn
    -0.07
     Intake
    -0.07
    POSITIVE LOGITS
     wildcard
    0.10
    Wildcard
    0.10
     mahimong
    0.09
    िष्य
    0.09
    Busqueda
    0.08
     termen
    0.08
     gyda
    0.08
    क
    0.08
     '*'
    0.08
     substitutions
    0.08
    Activations Density 0.005%

    No Known Activations