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. 111972
    Prev
    Next
    INDEX
    Explanations

    PG content or content type

    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
     leh
    -0.08
    ober
    -0.08
    hethe
    -0.08
    bite
    -0.08
    hetical
    -0.08
    gruppe
    -0.07
    groep
    -0.07
     Nemo
    -0.07
     eux
    -0.07
     nq
    -0.07
    POSITIVE LOGITS
     spilling
    0.08
     마
    0.08
    Compart
    0.08
    అ
    0.07
    大家
    0.07
     للف
    0.07
     ز
    0.07
    Interpolation
    0.07
    �
    0.07
     preserv
    0.07
    Activations Density 0.001%

    No Known Activations