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. 3-RESID-POST-AA
    6. 12500
    Prev
    Next
    INDEX
    Explanations

    Persia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BW
    -0.08
     evid
    -0.08
     fallback
    -0.07
     levi
    -0.07
    UP
    -0.07
    底
    -0.07
     DPS
    -0.07
    Fallback
    -0.07
     disc
    -0.07
    bing
    -0.07
    POSITIVE LOGITS
     Hitler
    0.09
     ભ
    0.08
    Gradu
    0.08
    _RUN
    0.08
     જગ્ય
    0.08
     смерт
    0.08
     historischen
    0.07
    heen
    0.07
     રંગ
    0.07
    િયન
    0.07
    Activations Density 0.001%

    No Known Activations