© 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. 19-RESID-POST-AA
    11. 19055
    Prev
    Next
    INDEX
    Explanations

    circ

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    the
    -0.11
     the
    -0.11
     these
    -0.10
     what
    -0.10
     both
    -0.10
    which
    -0.10
     those
    -0.09
    both
    -0.09
    哪
    -0.09
    what
    -0.09
    POSITIVE LOGITS
    (angle
    0.09
     তৈরি
    0.08
     Listener
    0.08
    _setopt
    0.08
    (dt
    0.08
    �讯
    0.08
    /year
    0.08
    _each
    0.08
     Danmark
    0.08
    /YYYY
    0.08
    Activations Density 0.008%

    No Known Activations