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. 90143
    Prev
    Next
    INDEX
    Explanations

    Harassment

    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
     Assim
    -0.08
     NEWS
    -0.08
     ergibt
    -0.08
     aluminum
    -0.07
     Patch
    -0.07
     Lithium
    -0.07
     Metal
    -0.07
    �
    -0.07
     ligt
    -0.07
     manganese
    -0.07
    POSITIVE LOGITS
     harassment
    0.13
     intimidation
    0.13
     intimid
    0.12
     bullying
    0.12
     insults
    0.11
     prejud
    0.11
     insulting
    0.11
     humili
    0.10
     verbally
    0.10
     intimidating
    0.10
    Activations Density 0.021%

    No Known Activations