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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19424
    Prev
    Next
    INDEX
    Explanations

    profile

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rainfall
    -0.10
     antibiotics
    -0.09
     precipitation
    -0.09
     tribut
    -0.08
     лекар
    -0.08
     litigation
    -0.08
    distributed
    -0.08
     напряж
    -0.08
     uprising
    -0.08
     overst
    -0.08
    POSITIVE LOGITS
    プロフィール
    0.23
    头像
    0.19
     profiel
    0.17
    .profile
    0.17
     profile
    0.16
    /profile
    0.16
    (Profile
    0.16
    .avatar
    0.15
    (profile
    0.15
    /avatar
    0.15
    Activations Density 0.052%

    No Known Activations