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. 74565
    Prev
    Next
    INDEX
    Explanations

    Physics and Chemistry

    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
     Sherman
    -0.08
     ім
    -0.08
    純
    -0.08
    gmail
    -0.08
     fifty
    -0.08
    balanced
    -0.08
    ])]↵
    -0.08
     driveway
    -0.08
    �
    -0.08
     emphasized
    -0.07
    POSITIVE LOGITS
     vibr
    0.12
     molecules
    0.11
     molecule
    0.11
     vibrations
    0.10
     molé
    0.10
     molecular
    0.09
     vibration
    0.09
     rotational
    0.09
     excitation
    0.09
     proprio
    0.08
    Activations Density 0.003%

    No Known Activations