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. 49298
    Prev
    Next
    INDEX
    Explanations

    emergency, needing help

    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
     summertime
    -0.09
     disagree
    -0.09
    consistent
    -0.08
     lifelong
    -0.08
    summer
    -0.08
    =(-
    -0.08
    usual
    -0.08
    全年
    -0.08
    winter
    -0.08
     проще
    -0.08
    POSITIVE LOGITS
     Hud
    0.09
    Delay
    0.09
     delayed
    0.09
    _delay
    0.09
     they've
    0.09
     waiting
    0.08
     Delay
    0.08
     ballistic
    0.08
     Herrn
    0.08
     delay
    0.08
    Activations Density 0.016%

    No Known Activations