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. 119581
    Prev
    Next
    INDEX
    Explanations

    legitimate

    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
     боя
    -0.09
    DCALL
    -0.09
    .called
    -0.08
     энер
    -0.08
     bata
    -0.08
     dara
    -0.08
     удар
    -0.08
    クリック
    -0.08
    @Inject
    -0.08
     суда
    -0.08
    POSITIVE LOGITS
     Kef
    0.07
     gewinnen
    0.07
     yep
    0.07
    Yep
    0.07
    -her
    0.07
     Interesse
    0.07
     Administrator
    0.07
     Motivation
    0.07
     désir
    0.07
     standpoint
    0.07
    Activations Density 0.004%

    No Known Activations