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. 45218
    Prev
    Next
    INDEX
    Explanations

    decrease

    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
    anne
    -0.08
    determ
    -0.08
    ות
    -0.08
    agma
    -0.08
    see
    -0.07
    지를
    -0.07
    tech
    -0.07
    stay
    -0.07
    feedback
    -0.07
     đấu
    -0.07
    POSITIVE LOGITS
     речи
    0.09
     внимания
    0.09
     libido
    0.09
     hobbies
    0.09
     дых
    0.09
     caliber
    0.08
     dritte
    0.08
     palms
    0.08
     secretion
    0.08
     संसार
    0.08
    Activations Density 0.009%

    No Known Activations