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. 55930
    Prev
    Next
    INDEX
    Explanations

    transporter

    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
     Pierce
    -0.08
     ses
    -0.08
     salvo
    -0.07
    SAL
    -0.07
     vox
    -0.07
    +="
    -0.07
     pand
    -0.07
     vliegt
    -0.07
    机场
    -0.07
    Sé
    -0.07
    POSITIVE LOGITS
     குற
    0.09
     minimizar
    0.08
    idepress
    0.08
     Efficiency
    0.08
     လ
    0.08
     уменьш
    0.07
     اللعبة
    0.07
     minimizing
    0.07
     极
    0.07
    хны
    0.07
    Activations Density 0.001%

    No Known Activations