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. 77539
    Prev
    Next
    INDEX
    Explanations

    exclude

    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
    棒
    -0.09
    リング
    -0.08
    ship
    -0.08
     competence
    -0.08
     �
    -0.07
    -0.07
     Anatomy
    -0.07
     disciplin
    -0.07
     Clínica
    -0.07
     MES
    -0.07
    POSITIVE LOGITS
    掉
    0.15
     undes
    0.09
     лиш
    0.09
     undesirable
    0.08
     unnecessary
    0.08
     khỏi
    0.08
    Et
    0.08
     obscene
    0.08
    adel
    0.08
     gen
    0.08
    Activations Density 0.009%

    No Known Activations