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. 120153
    Prev
    Next
    INDEX
    Explanations

    ='

    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
     tasteful
    -0.08
     Igual
    -0.08
     cosmet
    -0.08
    306
    -0.07
    .can
    -0.07
     Agencia
    -0.07
     possibilidade
    -0.07
     poko
    -0.07
    Parcel
    -0.07
     czyn
    -0.07
    POSITIVE LOGITS
     lime
    0.09
     ouro
    0.09
    厉
    0.08
     bed
    0.08
     gold
    0.08
    FFFF
    0.08
     beam
    0.08
    .xlabel
    0.07
     plotted
    0.07
     violin
    0.07
    Activations Density 0.002%

    No Known Activations