© 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. 29042
    Prev
    Next
    INDEX
    Explanations

    in

    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
     ನಿವ
    -0.09
     retention
    -0.08
     infraestrutura
    -0.08
     Paral
    -0.08
     incarceration
    -0.08
    xiv
    -0.08
     Zur
    -0.08
    .exchange
    -0.08
    运输
    -0.08
    Retention
    -0.08
    POSITIVE LOGITS
     cuyo
    0.08
     beschad
    0.08
    Boolean
    0.08
     dominating
    0.07
     botones
    0.07
    =root
    0.07
    (cs
    0.07
     protr
    0.07
    abab
    0.07
    .Byte
    0.07
    Activations Density 0.007%

    No Known Activations