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. 119149
    Prev
    Next
    INDEX
    Explanations

    offense

    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
    145
    -0.07
     Face
    -0.07
     Anne
    -0.07
     anne
    -0.07
    ดำ
    -0.07
     gaz
    -0.07
     Fell
    -0.07
    ND
    -0.07
    ined
    -0.07
     Duncan
    -0.07
    POSITIVE LOGITS
    ubber
    0.09
     stereotypes
    0.08
     offend
    0.08
     tari
    0.08
     מכ
    0.07
    掉
    0.07
     труда
    0.07
    [A
    0.07
    igheder
    0.07
     Tib
    0.07
    Activations Density 0.005%

    No Known Activations