© 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. 19153
    Prev
    Next
    INDEX
    Explanations

    ];

    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
     podría
    -0.08
     võiks
    -0.08
     pourrait
    -0.07
     culprit
    -0.07
     TECH
    -0.07
     nuisance
    -0.07
     podrían
    -0.07
    _suspend
    -0.07
     welzijn
    -0.07
     prism
    -0.07
    POSITIVE LOGITS
     memset
    0.19
    	memset
    0.18
     strcpy
    0.18
    	strcpy
    0.18
     snprintf
    0.16
     strncpy
    0.15
    	memcpy
    0.15
    	snprintf
    0.15
     memcpy
    0.14
    	sprintf
    0.14
    Activations Density 0.002%

    No Known Activations