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. 112302
    Prev
    Next
    INDEX
    Explanations

    Plaintext

    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
    纽
    -0.08
     shape
    -0.08
    adores
    -0.08
     shaping
    -0.07
    _shape
    -0.07
     excl
    -0.07
     Shooting
    -0.07
     exclude
    -0.07
    objects
    -0.07
    .Shape
    -0.07
    POSITIVE LOGITS
     unsecured
    0.13
    .password
    0.12
     plaintext
    0.12
    (password
    0.12
    password
    0.12
    密码
    0.11
    =password
    0.11
    _PASSWORD
    0.11
     openly
    0.11
    	password
    0.11
    Activations Density 0.012%

    No Known Activations