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. 130215
    Prev
    Next
    INDEX
    Explanations

    satire/hoaxes

    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
    Preference
    -0.09
    809
    -0.08
    Pd
    -0.08
     computes
    -0.08
    (Size
    -0.08
    .preference
    -0.08
     puedo
    -0.08
     Pd
    -0.07
    Opts
    -0.07
     Preference
    -0.07
    POSITIVE LOGITS
     fraudulent
    0.12
     sensational
    0.12
     misinformation
    0.12
    骗局
    0.12
     misleading
    0.12
     falsa
    0.12
     bogus
    0.11
     counterfeit
    0.11
     falsely
    0.11
     malicious
    0.11
    Activations Density 0.025%

    No Known Activations