© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 843
    Prev
    Next
    INDEX
    Explanations

    truffles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opi
    -0.09
    opia
    -0.09
     kung
    -0.08
     Kung
    -0.08
     Spect
    -0.08
    cry
    -0.07
     mada
    -0.07
     lagu
    -0.07
     Savings
    -0.07
    -pand
    -0.07
    POSITIVE LOGITS
    伍
    0.07
    ,col
    0.07
    ेर
    0.07
    contr
    0.07
     �
    0.07
     Featured
    0.07
     दुस
    0.07
     Howard
    0.07
     snd
    0.07
     offending
    0.07
    Activations Density 0.001%

    No Known Activations