Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18958
    Prev
    Next
    INDEX
    Explanations

    graphic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    That
    -0.08
     второй
    -0.08
     baixa
    -0.08
    Low
    -0.08
    imag
    -0.07
     fabricante
    -0.07
     regimen
    -0.07
    低
    -0.07
     low
    -0.07
    low
    -0.07
    POSITIVE LOGITS
     arenas
    0.09
    itchens
    0.09
     overarching
    0.09
    coles
    0.09
     persoas
    0.08
     ខែ
    0.08
    weddol
    0.08
    ៣
    0.08
    ոլոգ
    0.08
    лять
    0.08
    Activations Density 0.001%

    No Known Activations