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. 29941
    Prev
    Next
    INDEX
    Explanations

    antique

    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
    ingular
    -0.08
    tx
    -0.07
    ผล
    -0.07
     נת
    -0.07
    ništ
    -0.07
     Λ
    -0.07
    -0.07
    Λ
    -0.07
     uploading
    -0.07
     tumour
    -0.07
    POSITIVE LOGITS
     antique
    0.09
    _pointer
    0.08
     antiques
    0.08
    用品
    0.08
    isci
    0.08
     ANI
    0.08
    收藏
    0.08
     ornate
    0.08
    ecc
    0.08
    Pointers
    0.08
    Activations Density 0.005%

    No Known Activations