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. 112260
    Prev
    Next
    INDEX
    Explanations

    Calculations and remainders

    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
    ně
    -0.07
    vest
    -0.07
     Dara
    -0.07
     Größe
    -0.07
     hdr
    -0.07
    _xyz
    -0.07
     vest
    -0.07
    ѕ
    -0.07
    stream
    -0.07
     लेने
    -0.07
    POSITIVE LOGITS
     снова
    0.09
     nữa
    0.08
     новые
    0.08
    ambahkan
    0.08
     integrante
    0.08
     novamente
    0.08
     nuevo
    0.08
    again
    0.08
     новым
    0.08
    alance
    0.08
    Activations Density 0.029%

    No Known Activations