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. 104035
    Prev
    Next
    INDEX
    Explanations

    x

    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
    эры
    -0.09
     Hans
    -0.08
     prib
    -0.08
    juan
    -0.07
    _checkpoint
    -0.07
     🙂↵↵
    -0.07
     ultr
    -0.07
     TIP
    -0.07
    ernes
    -0.07
     Behaviour
    -0.07
    POSITIVE LOGITS
    �
    0.08
     কর
    0.08
     palco
    0.08
    式
    0.07
     गीत
    0.07
     deriving
    0.07
     अभिय
    0.07
    ので
    0.07
    下降
    0.07
    Right
    0.07
    Activations Density 0.030%

    No Known Activations