© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    Abstract

    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
    �
    -0.09
    ри
    -0.08
    pering
    -0.08
    그
    -0.07
    odle
    -0.07
     slime
    -0.07
    ర్స
    -0.07
     conviv
    -0.07
     slag
    -0.07
     preciso
    -0.07
    POSITIVE LOGITS
     crazy
    0.08
     wi
    0.08
     Mb
    0.08
    _FRAGMENT
    0.07
     Fau
    0.07
     Bach
    0.07
     saddle
    0.07
     Franc
    0.07
     Evil
    0.07
     asi
    0.07
    Activations Density 0.002%

    No Known Activations