© 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. 129421
    Prev
    Next
    INDEX
    Explanations

    reflections and quotes

    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
    Settings
    -0.09
     simul
    -0.08
    dst
    -0.08
     kuti
    -0.08
    -disabled
    -0.08
     során
    -0.08
     rollout
    -0.08
     Ende
    -0.08
     amak
    -0.08
    _SAN
    -0.07
    POSITIVE LOGITS
    提醒
    0.12
     timeless
    0.11
     reminding
    0.11
     resonates
    0.10
     reminder
    0.10
     echoed
    0.10
     Nietzsche
    0.09
     reminds
    0.09
     urging
    0.09
     advocating
    0.09
    Activations Density 0.037%

    No Known Activations