© 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. 31018
    Prev
    Next
    INDEX
    Explanations

    inequality

    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
     scripted
    -0.09
    Dip
    -0.09
    Evt
    -0.08
    .Script
    -0.08
     Dip
    -0.08
    Cli
    -0.08
    Dims
    -0.08
     looping
    -0.08
    Scripts
    -0.07
     discoveries
    -0.07
    POSITIVE LOGITS
     左
    0.09
     вверх
    0.09
     RHS
    0.08
    _BAD
    0.08
     =)
    0.08
    左
    0.07
    lad
    0.07
     जाएगा
    0.07
     உள்ள
    0.07
     دارای
    0.07
    Activations Density 0.008%

    No Known Activations