© 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. 68866
    Prev
    Next
    INDEX
    Explanations

    pent

    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
     Jah
    -0.08
     Serbia
    -0.07
     Miriam
    -0.07
     everlasting
    -0.07
     decorr
    -0.07
    ediator
    -0.07
     elevated
    -0.07
    +.
    -0.07
    dd
    -0.07
     positivity
    -0.07
    POSITIVE LOGITS
    Clamp
    0.09
     cliente
    0.08
     clamp
    0.08
     empresas
    0.08
    Sides
    0.08
     aanwe
    0.08
     Ofic
    0.08
     محل
    0.08
     lín
    0.08
     benodigde
    0.08
    Activations Density 0.001%

    No Known Activations