© 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. 13296
    Prev
    Next
    INDEX
    Explanations

    termite

    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
     fari
    -0.07
    WF
    -0.07
     Conf
    -0.07
    XF
    -0.07
     authentic
    -0.07
    SPELL
    -0.07
    729
    -0.07
    ావ
    -0.07
     ovo
    -0.07
     noch
    -0.07
    POSITIVE LOGITS
     gutter
    0.09
     freopen
    0.08
     fracture
    0.08
    uellement
    0.08
    년에
    0.08
    екті
    0.08
    isecond
    0.08
    Controllers
    0.08
     relocated
    0.08
    �
    0.07
    Activations Density 0.001%

    No Known Activations