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. 43440
    Prev
    Next
    INDEX
    Explanations

    Generating poems

    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
     дальнейшем
    -0.08
     политики
    -0.08
    .Http
    -0.08
     {$
    -0.08
     nust
    -0.08
     конкурент
    -0.07
    提前
    -0.07
     선정
    -0.07
     anex
    -0.07
     несколь
    -0.07
    POSITIVE LOGITS
     poema
    0.11
     fleeting
    0.11
     sorrow
    0.11
     essence
    0.11
     imaginar
    0.10
     словно
    0.10
     poetic
    0.10
     कविता
    0.10
     imagined
    0.10
     poets
    0.10
    Activations Density 0.076%

    No Known Activations