© 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. 68880
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     empower
    -0.08
     foss
    -0.08
    бирать
    -0.07
    iram
    -0.07
     Foss
    -0.07
     recom
    -0.07
     Empower
    -0.07
     blot
    -0.07
     Mega
    -0.07
    कट
    -0.07
    POSITIVE LOGITS
     imaginary
    0.10
    Closed
    0.09
    .imag
    0.08
    _hdl
    0.08
     Closed
    0.08
    Creat
    0.08
     creatividad
    0.08
    بداع
    0.08
     créativité
    0.08
    .cy
    0.08
    Activations Density 0.022%

    No Known Activations