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. 29876
    Prev
    Next
    INDEX
    Explanations

    1

    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
    °↵
    -0.08
     innoc
    -0.08
    .JSON
    -0.08
    status
    -0.08
    mkdir
    -0.07
    合法
    -0.07
    vel
    -0.07
     lawful
    -0.07
     জম
    -0.07
    .Normalize
    -0.07
    POSITIVE LOGITS
    -equipped
    0.08
     chipset
    0.08
     Peterson
    0.08
     العب
    0.08
     Amazing
    0.08
    עט
    0.08
     Epic
    0.08
     뛰
    0.08
     chevaux
    0.08
     �
    0.07
    Activations Density 0.001%

    No Known Activations