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. 15-RESID-POST-AA
    6. 19647
    Prev
    Next
    INDEX
    Explanations

    not equal to

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rotates
    -0.08
     सीट
    -0.08
     приобрести
    -0.08
    .Any
    -0.07
    乘
    -0.07
     कुन
    -0.07
     कुनै
    -0.07
    _rotate
    -0.07
     எந்த
    -0.07
    -eji
    -0.07
    POSITIVE LOGITS
     duas
    0.10
     deux
    0.10
     dois
    0.10
     zwei
    0.09
     দুটি
    0.09
     ત્રણ
    0.09
     two
    0.09
     três
    0.09
     drei
    0.09
     రెండు
    0.09
    Activations Density 0.005%

    No Known Activations