Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98024
    Prev
    Next
    INDEX
    Explanations

    пов

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guidelines
    -0.10
     fundo
    -0.08
     Guidelines
    -0.08
    反水
    -0.08
     faig
    -0.08
    ificando
    -0.08
     trato
    -0.08
    fica
    -0.08
    贴
    -0.07
    ione
    -0.07
    POSITIVE LOGITS
    ор
    0.10
    орот
    0.08
    asn
    0.07
    ോര്
    0.07
    Tree
    0.07
    orne
    0.07
    oru
    0.07
     BJ
    0.07
     insbesondere
    0.07
    ‘z
    0.07
    Activations Density 0.000%

    No Known Activations