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. 41964
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    .datetime
    -0.08
    .date
    -0.08
     Kont
    -0.08
    'impression
    -0.08
    'avenir
    -0.08
    elor
    -0.07
     jeweils
    -0.07
    {}".
    -0.07
    官方网址
    -0.07
     date
    -0.07
    POSITIVE LOGITS
     removing
    0.10
     removed
    0.09
     حذف
    0.09
     zmanjš
    0.09
     delet
    0.09
     감소
    0.09
     삭제
    0.09
     Removing
    0.09
    (remove
    0.09
     remov
    0.09
    Activations Density 0.002%

    No Known Activations