© 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. 19144
    Prev
    Next
    INDEX
    Explanations

    value

    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
    stry
    -0.08
    igrations
    -0.08
     tactics
    -0.08
    ング
    -0.07
     algorithms
    -0.07
    gestellt
    -0.07
    amera
    -0.07
     प्रम
    -0.07
    ihl
    -0.07
     processes
    -0.07
    POSITIVE LOGITS
     väärt
    0.24
     విల
    0.23
    -value
    0.23
    -values
    0.22
     value
    0.22
    	value
    0.22
     değer
    0.22
     արժեք
    0.22
     Werte
    0.21
     قيمة
    0.21
    Activations Density 0.106%

    No Known Activations