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. 11-RESID-POST-AA
    6. 45089
    Prev
    Next
    INDEX
    Explanations

    Women and relationships

    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
     Andere
    -0.09
    혼
    -0.08
     Соб
    -0.08
     Departure
    -0.08
    )은
    -0.08
     Weitere
    -0.07
     ausgezeichnet
    -0.07
     Literatur
    -0.07
     Homo
    -0.07
     homo
    -0.07
    POSITIVE LOGITS
    kie
    0.09
     demasi
    0.07
     slightest
    0.07
     excessive
    0.07
     tadi
    0.07
    too
    0.07
    slaught
    0.07
    との
    0.07
     conversion
    0.07
    e
    0.07
    Activations Density 0.001%

    No Known Activations