© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95056
    Prev
    Next
    INDEX
    Explanations

    parental controls

    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
     stör
    -0.09
    ¿
    -0.08
     statue
    -0.08
     trivial
    -0.08
     organizz
    -0.08
     organiza
    -0.08
     Ons
    -0.08
     ఉద్య
    -0.08
     Organ
    -0.07
     recic
    -0.07
    POSITIVE LOGITS
    权限
    0.09
    annage
    0.08
     supervised
    0.08
     toezicht
    0.08
    ternet
    0.08
     интернет
    0.08
     vetted
    0.08
     승인
    0.08
    aniques
    0.08
    permissions
    0.08
    Activations Density 0.015%

    No Known Activations