© 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. 11-RESID-POST-AA
    6. 68323
    Prev
    Next
    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    રે
    -0.08
    ையாக
    -0.07
    .label
    -0.07
    uale
    -0.07
    -0.07
    ushi
    -0.07
    リーズ
    -0.07
    மை
    -0.07
     washable
    -0.07
     категор
    -0.07
    POSITIVE LOGITS
    长度
    0.12
     length
    0.11
     Length
    0.11
     lengths
    0.11
    Length
    0.10
    _lengths
    0.10
    _length
    0.10
     lengte
    0.10
     lenght
    0.09
     lengthy
    0.09
    Activations Density 0.005%

    No Known Activations