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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110278
    Prev
    Next
    INDEX
    Explanations

    falling or catching oneself

    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
     writers
    -0.10
     ukur
    -0.09
    iphi
    -0.08
    ifers
    -0.08
    "net
    -0.08
     unanim
    -0.08
     Writers
    -0.08
     minibar
    -0.08
    unes
    -0.07
    writers
    -0.07
    POSITIVE LOGITS
     छल
    0.11
    Landing
    0.11
     downward
    0.11
     exhilar
    0.10
     catching
    0.10
     landing
    0.10
     plunge
    0.10
    Leap
    0.10
     aterr
    0.10
    _jump
    0.10
    Activations Density 0.033%

    No Known Activations