© 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. 23-RESID-POST-AA
    11. 50817
    Prev
    Next
    INDEX
    Explanations

    agg

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oureuse
    -0.09
    кили
    -0.09
     kalah
    -0.09
    ્બ
    -0.09
    	valid
    -0.08
    ариф
    -0.08
     verdadera
    -0.08
    ्ब
    -0.08
     réelle
    -0.08
    	next
    -0.08
    POSITIVE LOGITS
    ling
    0.12
    ings
    0.11
    yd
    0.11
    ied
    0.10
    ies
    0.10
    ying
    0.10
    ly
    0.10
    ys
    0.10
    ysg
    0.09
    yp
    0.09
    Activations Density 0.008%

    No Known Activations