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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 68024
    Prev
    Next
    INDEX
    Explanations

    2

    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
    leased
    -0.08
     دعوت
    -0.08
    cx
    -0.08
     cx
    -0.08
     Einladung
    -0.08
     ax
    -0.08
    خط
    -0.07
     رك
    -0.07
     hus
    -0.07
    иться
    -0.07
    POSITIVE LOGITS
     corrupt
    0.08
     attacks
    0.08
     liiga
    0.08
    _bloc
    0.08
     NSE
    0.08
     पल
    0.07
     blows
    0.07
    .deepcopy
    0.07
    攻击
    0.07
     prestação
    0.07
    Activations Density 0.055%

    No Known Activations