© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47372
    Prev
    Next
    INDEX
    Explanations

    social media algorithms

    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
    Password
    -0.09
    Ansi
    -0.08
     password
    -0.08
    password
    -0.08
     Mour
    -0.08
     suicide
    -0.08
     anal
    -0.08
     ascii
    -0.08
     abort
    -0.07
    ANSI
    -0.07
    POSITIVE LOGITS
     추천
    0.13
    推薦
    0.12
     recommandations
    0.11
    推荐
    0.11
     advertisements
    0.11
     推荐
    0.11
     Recommendations
    0.10
    相关推荐
    0.10
    recommend
    0.10
     Empfehlungen
    0.10
    Activations Density 0.048%

    No Known Activations