© 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. 91613
    Prev
    Next
    INDEX
    Explanations

    appraisal

    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
     tras
    -0.09
    orthy
    -0.08
     wyb
    -0.08
    lsa
    -0.08
     Bucc
    -0.08
     basada
    -0.07
    _based
    -0.07
    туа
    -0.07
     demands
    -0.07
     Obi
    -0.07
    POSITIVE LOGITS
     Immobilien
    0.10
     недвижимости
    0.09
     Dienstleistungen
    0.09
     נד
    0.09
     imobili
    0.09
     immobili
    0.09
     appraisal
    0.08
     commissioned
    0.08
     lâ
    0.08
     недвиж
    0.08
    Activations Density 0.005%

    No Known Activations