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. 449
    Prev
    Next
    INDEX
    Explanations

    odor

    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
     COB
    -0.08
     golfer
    -0.08
    <iostream
    -0.08
    财政
    -0.07
    /assert
    -0.07
     כסף
    -0.07
     Calder
    -0.07
     "/"
    -0.07
    ナ
    -0.07
     Barça
    -0.07
    POSITIVE LOGITS
     запах
    0.09
     smell
    0.08
     smells
    0.08
    leni
    0.08
    viol
    0.08
     molest
    0.08
     unpleasant
    0.08
    emon
    0.08
     mozz
    0.08
     scents
    0.08
    Activations Density 0.001%

    No Known Activations