© 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. 3-RESID-POST-AA
    11. 2963
    Prev
    Next
    INDEX
    Explanations

    mentality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sss
    -0.09
     AMA
    -0.08
     TAM
    -0.08
    細
    -0.08
    如下
    -0.08
    교
    -0.08
     PMI
    -0.07
    عال
    -0.07
    heus
    -0.07
    ਿਗ
    -0.07
    POSITIVE LOGITS
     claim
    0.07
     Chronicles
    0.07
    BCC
    0.07
     Cur
    0.07
     Dino
    0.07
     aque
    0.07
    	cr
    0.07
     bub
    0.07
     вер
    0.07
     ese
    0.07
    Activations Density 0.000%

    No Known Activations