© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49266
    Prev
    Next
    INDEX
    Explanations

    ]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mention
    -0.11
     જાણ
    -0.11
     connue
    -0.11
     conocida
    -0.11
     mention
    -0.11
    (input
    -0.10
    provide
    -0.10
    Inputs
    -0.10
     showcased
    -0.10
     conocido
    -0.10
    POSITIVE LOGITS
     You're
    0.19
    You're
    0.19
     you're
    0.17
    you're
    0.13
     Given
    0.13
     estás
    0.13
     You
    0.13
    You
    0.13
    Given
    0.12
     Você
    0.11
    Activations Density 0.028%

    No Known Activations