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. 98765
    Prev
    Next
    INDEX
    Explanations

    already

    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
     Konzentr
    -0.08
     marine
    -0.08
     concentr
    -0.08
     plötzlich
    -0.07
    deithasol
    -0.07
     condom
    -0.07
    hope
    -0.07
     évolution
    -0.07
     Api
    -0.07
    Covid
    -0.07
    POSITIVE LOGITS
     successfully
    0.09
     partly
    0.09
    .obtain
    0.08
     visas
    0.08
     partially
    0.08
    获得
    0.08
     Successfully
    0.08
    掉
    0.08
    得到
    0.08
    Successfully
    0.07
    Activations Density 0.040%

    No Known Activations