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. 53242
    Prev
    Next
    INDEX
    Explanations

    emotional

    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
    ntag
    -0.08
    Friendly
    -0.08
    ngua
    -0.08
    Sponsored
    -0.07
     Slide
    -0.07
     airplane
    -0.07
    াক্ত
    -0.07
    versation
    -0.07
    �
    -0.07
    islation
    -0.07
    POSITIVE LOGITS
    因素
    0.10
     factoren
    0.09
     onvoldoende
    0.09
     Faktoren
    0.08
     insufficient
    0.08
     विश्वास
    0.08
     estrés
    0.08
    综合
    0.08
     facteurs
    0.08
    .activ
    0.08
    Activations Density 0.014%

    No Known Activations