© 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 EvalsExportsinterp-engineNEWAPI 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. 110353
    Prev
    Next
    INDEX
    Explanations

    Building facades and cladding

    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
     acquaintances
    -0.09
     minas
    -0.09
     ગીત
    -0.09
     baile
    -0.09
     habilidades
    -0.09
     เต
    -0.08
    Songs
    -0.08
     rever
    -0.08
     લગ્ન
    -0.08
     знакомства
    -0.08
    POSITIVE LOGITS
     ткани
    0.09
    .body
    0.09
     frontage
    0.08
     façade
    0.08
    .transparent
    0.08
    外
    0.08
     uitstraling
    0.08
    .shadow
    0.08
     veneer
    0.08
    .semantic
    0.08
    Activations Density 0.013%

    No Known Activations