© 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. 18577
    Prev
    Next
    INDEX
    Explanations

    inline

    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
     verkrij
    -0.08
    desired
    -0.08
    Desired
    -0.08
     gewenste
    -0.08
    ’aller
    -0.08
    icions
    -0.08
     dolo
    -0.08
    directive
    -0.07
     მოც
    -0.07
    bug
    -0.07
    POSITIVE LOGITS
     inline
    0.17
     Inline
    0.16
    .inline
    0.15
    Inline
    0.15
    inline
    0.14
    	inline
    0.14
    -inline
    0.13
    _inline
    0.12
    _INLINE
    0.12
     INLINE
    0.12
    Activations Density 0.001%

    No Known Activations