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. 45718
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
     accomplishment
    -0.09
     compromisso
    -0.08
    ullan
    -0.08
     attainment
    -0.08
     ব্যবস্থা
    -0.08
    ....
    -0.08
     adequado
    -0.07
    .....
    -0.07
     ઉપયોગ
    -0.07
     violence
    -0.07
    POSITIVE LOGITS
    凉
    0.09
     angenehm
    0.09
     warmed
    0.08
     ERR
    0.08
     приятно
    0.08
     Ober
    0.08
     ioutil
    0.08
     Sensitive
    0.08
     grazing
    0.08
     тепл
    0.08
    Activations Density 0.014%

    No Known Activations