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. 77471
    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
    isuus
    -0.08
     kayan
    -0.08
    izacao
    -0.07
    zon
    -0.07
     tante
    -0.07
     모습을
    -0.07
    ませ
    -0.07
     benöt
    -0.07
     facteur
    -0.07
    收益
    -0.07
    POSITIVE LOGITS
    >The
    0.07
     �
    0.07
    >This
    0.07
     
    0.07
     Initial
    0.07
    >Please
    0.07
     уст
    0.07
     oscill
    0.07
     Includes
    0.07
    >",
    0.07
    Activations Density 0.012%

    No Known Activations