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. 65192
    Prev
    Next
    INDEX
    Explanations

    claws

    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
     frequência
    -0.10
     fréquence
    -0.08
     flux
    -0.07
     Cross
    -0.07
     inflação
    -0.07
     Microwave
    -0.07
     desloc
    -0.07
     Expanded
    -0.07
     factual
    -0.07
    Asked
    -0.07
    POSITIVE LOGITS
     claws
    0.10
     sharper
    0.09
     vicious
    0.09
    尖
    0.09
     �
    0.09
     finger
    0.09
    刺
    0.08
    CDATA
    0.08
     devastating
    0.08
     damaging
    0.08
    Activations Density 0.009%

    No Known Activations