Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106319
    Prev
    Next
    INDEX
    Explanations

    credentials

    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
     sham
    -0.08
     espal
    -0.08
     camouflage
    -0.08
     استراتيجية
    -0.08
    Atom
    -0.07
    疯狂
    -0.07
     lore
    -0.07
     dirt
    -0.07
     chase
    -0.07
     sht
    -0.07
    POSITIVE LOGITS
     Credential
    0.10
    Credential
    0.10
    >Password
    0.09
    _PASSWORD
    0.09
    밀번호
    0.09
    Password
    0.09
     passwords
    0.09
     пароль
    0.09
    ,password
    0.09
    -password
    0.08
    Activations Density 0.004%

    No Known Activations