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. 53418
    Prev
    Next
    INDEX
    Explanations

    a

    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
     није
    -0.08
     Shoulder
    -0.08
     "";↵
    -0.08
     Ket
    -0.08
    amera
    -0.08
     Saber
    -0.07
     Rig
    -0.07
     Hmm
    -0.07
    Hover
    -0.07
     boulot
    -0.07
    POSITIVE LOGITS
     eg
    0.07
    ご
    0.07
     simpler
    0.07
     Swiss
    0.07
     bew
    0.07
     necessariamente
    0.07
     സംഭ
    0.07
     gam
    0.07
     medizin
    0.06
    読
    0.06
    Activations Density 0.076%

    No Known Activations