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. 117532
    Prev
    Next
    INDEX
    Explanations

    Hz

    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
     पह
    -0.09
     Coke
    -0.08
     welfare
    -0.08
    策
    -0.07
     bato
    -0.07
    -us
    -0.07
    yaa
    -0.07
    去年
    -0.07
     kud
    -0.07
    팔
    -0.07
    POSITIVE LOGITS
    Hz
    0.08
     Rib
    0.08
     performers
    0.08
     Burst
    0.08
     descriptor
    0.07
     ν
    0.07
     Basis
    0.07
    Basis
    0.07
     Hz
    0.07
     nu
    0.07
    Activations Density 0.003%

    No Known Activations