© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47479
    Prev
    Next
    INDEX
    Explanations

    destruction, removal

    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
     mõju
    -0.10
     અસર
    -0.09
    _inverse
    -0.09
     효과
    -0.09
     असर
    -0.09
     ציבור
    -0.09
     առ
    -0.08
     эфф
    -0.08
    荐
    -0.08
    ψεις
    -0.08
    POSITIVE LOGITS
     destroyed
    0.19
    Destroyed
    0.15
     navigating
    0.15
     removed
    0.14
     loses
    0.14
     destroys
    0.14
     уничтож
    0.14
     destroying
    0.14
     deleted
    0.14
     disposed
    0.13
    Activations Density 0.019%

    No Known Activations