© 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. 21860
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    =>$
    -0.09
     saavad
    -0.08
    న్ని
    -0.08
    ertungen
    -0.08
     hökm
    -0.08
    oloogia
    -0.08
     sustain
    -0.08
    ünscht
    -0.08
    ?)
    -0.08
    )"
    -0.08
    POSITIVE LOGITS
    kod
    0.08
     '↵↵
    0.08
    922
    0.07
    *****↵↵
    0.07
     '}↵
    0.07
    491
    0.07
    ################################################################################
    0.07
    584
    0.07
    anay
    0.07
    302
    0.07
    Activations Density 0.000%

    No Known Activations