Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77559
    Prev
    Next
    INDEX
    Explanations

    drain

    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
    lof
    -0.08
    Illuminate
    -0.07
    -0.07
    �
    -0.07
     thể
    -0.07
     relazione
    -0.07
    テゴ
    -0.07
     famil
    -0.07
    Wanted
    -0.07
    Undefined
    -0.07
    POSITIVE LOGITS
    ออก
    0.08
    orse
    0.08
     BAG
    0.07
    christ
    0.07
     Clem
    0.07
    ide
    0.07
     Weg
    0.07
     Sø
    0.07
     Martin
    0.07
     Sud
    0.07
    Activations Density 0.004%

    No Known Activations